# Microsoft Security

Expert coverage of cybersecurity topics

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Microsoft named a Leader in the 2026 Gartner® Magic Quadrant™ for SIEM

DevFeed: [Microsoft named a Leader in the 2026 Gartner® Magic Quadrant™ for SIEM](<https://devfeed.tech/articles/microsoft-named-a-leader-in-the-2026-gartner-magic-quadranttm-for-siem-146679.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/11/20/microsoft-named-a-leader-in-the-2026-gartner-magic-quadrant-for-siem/>)

Author: Rob Lefferts

Published: 2026-11-20T17:00:00Z

Content type: article

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [Security Information and Event Management (SIEM)](<https://devfeed.tech/topics/siem-security.md>), [alert triage](<https://devfeed.tech/topics/alert-triage.md>), [Threat monitoring](<https://devfeed.tech/topics/threat-monitoring.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-soc](<https://devfeed.tech/tags/agentic-soc.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [alert-triage](<https://devfeed.tech/tags/alert-triage.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [attack-disruption](<https://devfeed.tech/tags/attack-disruption.md>), [automation](<https://devfeed.tech/tags/automation.md>), [blog](<https://devfeed.tech/tags/blog.md>), [business-email-compromise](<https://devfeed.tech/tags/business-email-compromise.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [gartner](<https://devfeed.tech/tags/gartner.md>), [gartner-magic-quadrant](<https://devfeed.tech/tags/gartner-magic-quadrant.md>), [gartner-magic-quadranttm](<https://devfeed.tech/tags/gartner-magic-quadranttm.md>), [leader](<https://devfeed.tech/tags/leader.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [security](<https://devfeed.tech/tags/security.md>), [security-blog](<https://devfeed.tech/tags/security-blog.md>), [security-information-and-event-management](<https://devfeed.tech/tags/security-information-and-event-management.md>), [siem](<https://devfeed.tech/tags/siem.md>)

### AI overview

Microsoft says it was named a Leader in the 2026 Gartner Magic Quadrant for SIEM. Its post describes Microsoft Sentinel as a cloud-native SIEM with more than 500 Microsoft and third-party connectors, built-in detections, threat hunting and response capabilities, and a data lake for historical and real-time security data. Microsoft also describes the Integrated Security Operations Center (ISOC) in Defender, introduced September 23, 2026, as combining Sentinel SIEM with XDR, threat intelligence, posture management, and response. The post says Defender can correlate signals and automatically contain compromised users and devices in high-confidence attacks, reporting an average ransomware disruption time of 30 seconds across customers. It presents AI agents as supporting tasks such as threat hunting, triage, and investigations, with people providing judgment and accountability. These recognition and performance statements are Microsoft's claims in the supplied text.

### Source excerpt

We're honored that Microsoft has once again been recognized as a Leader in the 2026 Gartner® Magic Quadrant™ for Security Information and Event Management (SIEM). The post Microsoft named a Leader in the 2026 Gartner® Magic Quadrant™ for SIEM appeared first on Microsoft Security Blog.

## The risks of device code authentication for AI coding agents

DevFeed: [The risks of device code authentication for AI coding agents](<https://devfeed.tech/articles/the-risks-of-device-code-authentication-for-ai-coding-agents-138244.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/11/17/the-risks-of-device-code-authentication-for-ai-coding-agents/>)

Author: Microsoft Security Research

Published: 2026-11-17T15:00:00Z

Content type: news

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [Credential theft](<https://devfeed.tech/topics/credential-theft.md>), [GitHub Copilot CLI](<https://devfeed.tech/topics/github-copilot-cli.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Authentication](<https://devfeed.tech/topics/authentication.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [blog](<https://devfeed.tech/tags/blog.md>), [can](<https://devfeed.tech/tags/can.md>), [ci-cd](<https://devfeed.tech/tags/ci-cd.md>), [cli](<https://devfeed.tech/tags/cli.md>), [client](<https://devfeed.tech/tags/client.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [device](<https://devfeed.tech/tags/device.md>), [device-code](<https://devfeed.tech/tags/device-code.md>), [device-code-phishing](<https://devfeed.tech/tags/device-code-phishing.md>), [example](<https://devfeed.tech/tags/example.md>), [flow](<https://devfeed.tech/tags/flow.md>), [github](<https://devfeed.tech/tags/github.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [phishing](<https://devfeed.tech/tags/phishing.md>), [social-engineering](<https://devfeed.tech/tags/social-engineering.md>), [token-theft](<https://devfeed.tech/tags/token-theft.md>)

### AI overview

In a controlled lab, researchers showed that approving an attacker-started GitHub device-code request could expose a Copilot CLI user's repositories and synced sessions, let misleading memory entries affect later interactions, or enable remote steering of an active session. Each outcome depends on account permissions and enabled features; remote steering also requires an active online session, remote control enabled, and organization policy allowing it. These are proof-of-concept results, not attacks observed in the wild, and the device-flow phishing technique can target any public client that supports the flow. Users should approve only sign-ins they initiated. Organizations can review and revoke unexpected OAuth grants, limit repository access, review session and memory settings, and connect GitHub Enterprise Cloud to Defender for Cloud Apps to support investigations. Detection and disruption capabilities require supported configurations and integrations.

### Source excerpt

Lab research shows how device code phishing, a technique that applies to any device-flow client, can extend to AI coding agents, using GitHub Copilot CLI as an illustrative example. The post The risks of device code authentication for AI coding agents appeared first on Microsoft Security Blog.

## High volume phishing campaign uses Microsoft 365 outage lures to target multiple industry sectors

DevFeed: [High volume phishing campaign uses Microsoft 365 outage lures to target multiple industry sectors](<https://devfeed.tech/articles/high-volume-phishing-campaign-uses-microsoft-365-outage-lures-to-target-multiple-industry-sectors-138243.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/11/16/high-volume-phishing-campaign-uses-microsoft-365-outage-lures-target-multiple-industry-sectors-2/>)

Author: Shreya Kale

Published: 2026-11-17T00:08:41Z

Content type: news

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [Threat monitoring](<https://devfeed.tech/topics/threat-monitoring.md>), [microsoft 365](<https://devfeed.tech/topics/microsoft-365.md>), [Microsoft](<https://devfeed.tech/topics/microsoft.md>), [alert triage](<https://devfeed.tech/topics/alert-triage.md>)

Tags: [campaign](<https://devfeed.tech/tags/campaign.md>), [credential-theft](<https://devfeed.tech/tags/credential-theft.md>), [incident-response](<https://devfeed.tech/tags/incident-response.md>), [industry](<https://devfeed.tech/tags/industry.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [microsoft-365](<https://devfeed.tech/tags/microsoft-365.md>), [microsoft-365-outage](<https://devfeed.tech/tags/microsoft-365-outage.md>), [multiple](<https://devfeed.tech/tags/multiple.md>), [outage](<https://devfeed.tech/tags/outage.md>), [phishing](<https://devfeed.tech/tags/phishing.md>), [social-engineering](<https://devfeed.tech/tags/social-engineering.md>), [target](<https://devfeed.tech/tags/target.md>), [threat-intelligence](<https://devfeed.tech/tags/threat-intelligence.md>), [volume](<https://devfeed.tech/tags/volume.md>)

### AI overview

On November 13, 2026, Microsoft observed a high-volume phishing campaign impersonating Microsoft 365 service-health notices. Emails claimed messages were held during an outage and would be deleted within 24 hours, urging recipients to click a restore link that redirected through tracking URLs to a non-Microsoft site. Microsoft assessed likely credential phishing, but the supplied evidence did not confirm credential capture, malware delivery, or post-compromise activity. Defender blocks or quarantines the campaign messages and domains. Microsoft advises searching for and removing matching email, reviewing click and account activity, and resetting credentials and revoking sessions if users may have entered them. It also recommends MFA, Safe Links and Safe Attachments, and ZAP. Avoid broad blocks of shared delivery infrastructure without corroborating signals.

### Source excerpt

Microsoft Threat Intelligence observed a high-volume phishing campaign using Microsoft 365 outage-themed lures to target organizations across multiple sectors worldwide. The post High volume phishing campaign uses Microsoft 365 outage lures to target multiple industry sectors appeared first on Microsoft Security Blog.

## Trained to betray: How post-training supply chain attacks hijack coding agents

DevFeed: [Trained to betray: How post-training supply chain attacks hijack coding agents](<https://devfeed.tech/articles/trained-to-betray-how-post-training-supply-chain-attacks-hijack-coding-agents-131419.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/11/12/trained-to-betray-how-post-training-supply-chain-attacks-hijack-coding-agents/>)

Author: Microsoft Security Research, Microsoft AI Red Team, Amanda Minnich, Amit Eliahu, Blake Bullwinkel, Dor Edry and Giorgio Severi

Published: 2026-11-12T17:00:00Z

Content type: article

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [post-training](<https://devfeed.tech/topics/post-training.md>), [AI software supply chain security](<https://devfeed.tech/topics/ai-software-supply-chain-security.md>), [Adversarial attacks](<https://devfeed.tech/topics/adversarial-attacks.md>), [supply-chain-security](<https://devfeed.tech/topics/supply-chain-security.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>)

Tags: [activation](<https://devfeed.tech/tags/activation.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-harnesses](<https://devfeed.tech/tags/agent-harnesses.md>), [agent-security](<https://devfeed.tech/tags/agent-security.md>), [ai-red-team](<https://devfeed.tech/tags/ai-red-team.md>), [attack](<https://devfeed.tech/tags/attack.md>), [attack-paths](<https://devfeed.tech/tags/attack-paths.md>), [backdoor](<https://devfeed.tech/tags/backdoor.md>), [backdoors](<https://devfeed.tech/tags/backdoors.md>), [code-execution](<https://devfeed.tech/tags/code-execution.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [post-training](<https://devfeed.tech/tags/post-training.md>), [remote-code-execution](<https://devfeed.tech/tags/remote-code-execution.md>), [security](<https://devfeed.tech/tags/security.md>), [supply-chain-attack](<https://devfeed.tech/tags/supply-chain-attack.md>), [supply-chain-attacks](<https://devfeed.tech/tags/supply-chain-attacks.md>), [trigger](<https://devfeed.tech/tags/trigger.md>)

### AI overview

Two studies show that post-training supply-chain attacks can make coding agents misuse tools while appearing to handle benign tasks. Dataset poisoning plants crafted examples in data used by the victim: about 1% poisoned examples produced roughly 78% attack success on seen harnesses, with transfer to one unseen harness but none to another. Model poisoning assumes attacker control of training and a distributed checkpoint; stronger configurations reached 84.1%-94.8% success on unseen repositories, and results varied across coding harnesses. Reinforcement learning recovered much of benign-task utility without substantially reducing the backdoor in the tested setup. The studies support reviewing and pinning training data, tracking checkpoint provenance, evaluating in the production harness with trigger variations, and limiting tool permissions, credentials, files, and network access. Runtime monitoring, isolation, and approval for consequential actions add controls at execution time.

### Source excerpt

Microsoft Defender Research and the AI Red Team discuss how poisoned datasets and poisoned model checkpoints can trigger remote code execution and other malicious activities. The post Trained to betray: How post-training supply chain attacks hijack coding agents appeared first on Microsoft Security Blog.

## The global socket: how threat actors are weaponizing GSocket for stealthy C2

DevFeed: [The global socket: how threat actors are weaponizing GSocket for stealthy C2](<https://devfeed.tech/articles/the-global-socket-how-threat-actors-are-weaponizing-gsocket-for-stealthy-c2-129704.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/11/11/global-socket-how-threat-actors-weaponizing-gsocket-stealthy-c2/>)

Author: Yash Gund, Sumith Maniath and Microsoft Security Research

Published: 2026-11-11T19:49:57Z

Content type: article

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Threat monitoring](<https://devfeed.tech/topics/threat-monitoring.md>), [Cybercrime](<https://devfeed.tech/topics/cybercrime.md>)

Tags: [c2](<https://devfeed.tech/tags/c2.md>), [gsocket](<https://devfeed.tech/tags/gsocket.md>), [linux](<https://devfeed.tech/tags/linux.md>), [remote](<https://devfeed.tech/tags/remote.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

Microsoft reports that attackers use GSocket to retain access to compromised Linux servers after the initial application vulnerability is patched. The client and operator connect outbound through a shared public relay, using a shared secret to establish an encrypted session; this avoids fixed attacker-owned IPs or domains, inbound listeners, and dedicated C2 infrastructure. Observed deployments included disguised processes, staging in writable or memory-backed paths, layered persistence, and occasional attempts to exploit CVE-2026-43284 for root access. In Microsoft Defender for Endpoint telemetry, detections rose 356.2% from March through August 2026, and web applications and hosting made up 87.1% of attributable incidents; these figures describe the analyzed telemetry, and attack stages varied. Guidance includes investigating the host and removing GSocket and persistence alongside patching, restricting and monitoring outbound traffic, auditing cron, systemd, and shell startup files, and using Defender telemetry and hunting queries to investigate activity.

### Source excerpt

Threat actors are deploying GSocket on compromised Linux servers to keep encrypted remote access after the original vulnerability is patched. Learn how to detect, investigate, and remediate this activity. The post The global socket: how threat actors are weaponizing GSocket for stealthy C2 appeared first on Microsoft Security Blog.

## Lessons from 59 Linux Kernel Bug Reports

DevFeed: [Lessons from 59 Linux Kernel Bug Reports](<https://devfeed.tech/articles/lessons-from-59-linux-kernel-bug-reports-129705.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/11/11/lessons-from-59-linux-kernel-bug-reports/>)

Author: FORGE Lab and Cen Zhang

Published: 2026-11-11T16:55:00Z

Content type: article

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [Linux Kernel](<https://devfeed.tech/topics/linux-kernel.md>), [code security](<https://devfeed.tech/topics/code-security.md>), [Linux](<https://devfeed.tech/topics/linux.md>), [Security](<https://devfeed.tech/topics/security.md>), [Memory Safety](<https://devfeed.tech/topics/memory-safety.md>), [experience report](<https://devfeed.tech/topics/experience-report.md>), [SELinux](<https://devfeed.tech/topics/selinux.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [bug](<https://devfeed.tech/tags/bug.md>), [bug-reports](<https://devfeed.tech/tags/bug-reports.md>), [codename](<https://devfeed.tech/tags/codename.md>), [cves](<https://devfeed.tech/tags/cves.md>), [exploits](<https://devfeed.tech/tags/exploits.md>), [first](<https://devfeed.tech/tags/first.md>), [forge](<https://devfeed.tech/tags/forge.md>), [frontier-ai-models](<https://devfeed.tech/tags/frontier-ai-models.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [lab](<https://devfeed.tech/tags/lab.md>), [linux](<https://devfeed.tech/tags/linux.md>), [linux-kernel](<https://devfeed.tech/tags/linux-kernel.md>), [local](<https://devfeed.tech/tags/local.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [post](<https://devfeed.tech/tags/post.md>), [privilege-escalation](<https://devfeed.tech/tags/privilege-escalation.md>), [reports](<https://devfeed.tech/tags/reports.md>), [research](<https://devfeed.tech/tags/research.md>), [root](<https://devfeed.tech/tags/root.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

Microsoft FORGE Lab's MDASH scans of selected Linux kernel subsystems produced 26,502 raw findings in about two weeks. Screening and QEMU reproduction narrowed these to 621 PoC-backed cases; expert review yielded 59 upstream reports and 33 assigned CVEs, including eight with confirmed local root exploits. Fixing them required months of researcher and maintainer work: 38 reports have merged fixes, and the median time from first public patch to a mainline release was 41 days. The excerpt's CVE-2026-64563 example traces an eight-year-old rhashtable iterator bug to a missing pointer reset on one resume path; a reachable Netlink socket diagnostics caller made it exploitable. The researchers conclude that AI-assisted discovery can expand vulnerability research, but validating, reporting, and fixing findings remains human-intensive. The work covered only a subset of the kernel, and the authors say findings alone do not establish that the system is secure.

### Source excerpt

Microsoft FORGE Lab researchers used codename MDASH to investigate Linux kernel vulnerabilities, resulting in 59 upstream bug reports, 33 assigned CVEs, and 38 merged fixes. The research includes eight demonstrated local root privilege-escalation exploits and examines the challenges of turning AI-generated findings into validated vulnerabilities and upstream fixes. The post Lessons from 59 Linux Kernel Bug Reports appeared first on Microsoft Security Blog.

## Detecting sleeper agents hiding in AI model neurons

DevFeed: [Detecting sleeper agents hiding in AI model neurons](<https://devfeed.tech/articles/detecting-sleeper-agents-hiding-in-ai-model-neurons-129703.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/11/10/detecting-sleeper-agents-hiding-in-ai-model-neurons/>)

Author: Microsoft Threat Intelligence

Published: 2026-11-10T23:00:00Z

Content type: news

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>), [prompt injection](<https://devfeed.tech/topics/prompt-injection.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-model](<https://devfeed.tech/tags/ai-model.md>), [also](<https://devfeed.tech/tags/also.md>), [blog](<https://devfeed.tech/tags/blog.md>), [can](<https://devfeed.tech/tags/can.md>), [edits](<https://devfeed.tech/tags/edits.md>), [fewer](<https://devfeed.tech/tags/fewer.md>), [found](<https://devfeed.tech/tags/found.md>), [frontier](<https://devfeed.tech/tags/frontier.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [microsoft-research](<https://devfeed.tech/tags/microsoft-research.md>), [model](<https://devfeed.tech/tags/model.md>), [payload](<https://devfeed.tech/tags/payload.md>), [post](<https://devfeed.tech/tags/post.md>), [research](<https://devfeed.tech/tags/research.md>), [security](<https://devfeed.tech/tags/security.md>), [this](<https://devfeed.tech/tags/this.md>), [threat-research](<https://devfeed.tech/tags/threat-research.md>)

### AI overview

Microsoft Research describes a model backdoor made by editing fewer than 10 neurons: the model can pass evaluations, then execute an attacker's command when a trigger appears in context, using the agent's available access. The attack requires only inference-capable hardware; Microsoft says it has not observed threat actors using it. Frontier agents can identify anomalous weight edits, though passing an audit does not guarantee safe behavior. Recommended defenses include diffing checkpoints against verifiable base models before deployment and after updates, adding behavioral backdoor scans and trigger tests, and treating third-party models as untrusted until audited. The guidance also calls for least-privilege agent identities, isolated code execution, restricted network egress, human approval for high-impact actions, and runtime monitoring. Microsoft's Defender scanning covers serialization and code-level risks and complements, but does not replace, weight-level audits.

### Source excerpt

Microsoft Research has released new threat research detailing how a capable agent model could be turned into a sleeper agent by editing fewer than ten neurons to inject a short payload; Microsoft Research has also found that this threat is detectable by frontier agents, which can identify anomalous weight edits. The post Detecting sleeper agents hiding in AI model neurons appeared first on Microsoft Security Blog.

## FORGE Lab uses agentic tools to identify memory safety issues in Rust

DevFeed: [FORGE Lab uses agentic tools to identify memory safety issues in Rust](<https://devfeed.tech/articles/forge-lab-uses-agentic-tools-to-identify-memory-safety-issues-in-rust-124340.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/11/09/forge-lab-uses-agentic-tools-to-identify-memory-safety-issues-in-rust/>)

Author: Yechan Bae and FORGE Lab

Published: 2026-11-09T20:17:31Z

Content type: article

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [Memory Safety](<https://devfeed.tech/topics/memory-safety.md>), [Memory safety verification](<https://devfeed.tech/topics/memory-safety-verification.md>), [Rust](<https://devfeed.tech/topics/rust.md>), [software security audit](<https://devfeed.tech/topics/software-security-audit.md>), [Tool](<https://devfeed.tech/topics/tool.md>), [Static code analysis](<https://devfeed.tech/topics/static-code-analysis.md>), [Microsoft](<https://devfeed.tech/topics/microsoft.md>), [ai code review](<https://devfeed.tech/topics/ai-code-review.md>)

Tags: [2015](<https://devfeed.tech/tags/2015.md>), [2020](<https://devfeed.tech/tags/2020.md>), [2021](<https://devfeed.tech/tags/2021.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-security](<https://devfeed.tech/tags/agentic-security.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [ai-powered](<https://devfeed.tech/tags/ai-powered.md>), [analyzer](<https://devfeed.tech/tags/analyzer.md>), [android](<https://devfeed.tech/tags/android.md>), [api](<https://devfeed.tech/tags/api.md>), [apis](<https://devfeed.tech/tags/apis.md>), [bugs](<https://devfeed.tech/tags/bugs.md>), [forge](<https://devfeed.tech/tags/forge.md>), [frontier-ai-models](<https://devfeed.tech/tags/frontier-ai-models.md>), [memory-safety](<https://devfeed.tech/tags/memory-safety.md>), [research](<https://devfeed.tech/tags/research.md>), [rust](<https://devfeed.tech/tags/rust.md>), [security](<https://devfeed.tech/tags/security.md>), [tools](<https://devfeed.tech/tags/tools.md>), [undefined-behavior](<https://devfeed.tech/tags/undefined-behavior.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>)

### AI overview

Microsoft FORGE Lab used Hyenas, its research version of codename MDASH, to help investigate and validate Rust standard-library soundness bugs. The researchers group the failures into three patterns: unsafe code may unwind while an invariant is broken; it may rely on caller-provided safe implementations behaving correctly; or it may assume operating-system and process-wide state remains unchanged. Examples include a panic during `MapWindows::clone` exposing uninitialized values to a destructor, a custom `Pattern` producing invalid UTF-8 through `str::replace`, and process cleanup unmapping the main thread's signal stack. The article also describes environment races in `CommandExt::exec`. Rust maintainers fixed or reviewed several reported issues; at publication, two team-reported issues remained open. The authors stress that a soundness bug is not automatically an exploitable vulnerability: triggering the reported cases may require unusual conditions, and they found no reliable exploitation path for the signal-stack issue under the conditions examined. They argue that AI-assisted analysis can help search system boundaries that traditional static analysis has difficulty modeling.

### Source excerpt

Microsoft FORGE Lab researchers found memory-safety bugs in Rust's core and std libraries, including cases where safe Rust code can trigger undefined behavior. Using Hyenas, FORGE's frontier research version of codename MDASH, the team investigated three patterns of misplaced trust in unsafe code and what they reveal about Rust's safety guarantees. The post FORGE Lab uses agentic tools to identify memory safety issues in Rust appeared first on Microsoft Security Blog.

## ARTEX abuse expands as cybercriminals target financial sector

DevFeed: [ARTEX abuse expands as cybercriminals target financial sector](<https://devfeed.tech/articles/artex-abuse-expands-as-cybercriminals-target-financial-sector-122030.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/11/06/artex-abuse-expands-as-cybercriminals-target-financial-sector/>)

Author: Microsoft Threat Intelligence

Published: 2026-11-07T02:44:34Z

Content type: news

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [Security, Privacy and Abuse Prevention](<https://devfeed.tech/topics/security-privacy-and-abuse-prevention.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>), [credential-based attacks](<https://devfeed.tech/topics/credential-based-attacks.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Threat monitoring](<https://devfeed.tech/topics/threat-monitoring.md>), [password spraying](<https://devfeed.tech/topics/password-spraying.md>), [alert triage](<https://devfeed.tech/topics/alert-triage.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [actor](<https://devfeed.tech/tags/actor.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [artex](<https://devfeed.tech/tags/artex.md>), [credential-theft](<https://devfeed.tech/tags/credential-theft.md>), [financial](<https://devfeed.tech/tags/financial.md>), [financial-sector](<https://devfeed.tech/tags/financial-sector.md>), [framework](<https://devfeed.tech/tags/framework.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [october-2026](<https://devfeed.tech/tags/october-2026.md>), [storm](<https://devfeed.tech/tags/storm.md>), [target](<https://devfeed.tech/tags/target.md>)

### AI overview

Microsoft reports that Storm-3358 began using ARTEX against financial organizations in October 2026, combining agentic scanning and exploitation with conventional tools to deploy RATs, establish persistence, move laterally, and exfiltrate data. Reported activity includes exploiting web application flaws, abusing credentials and cloud identities, and brute-force or password-spraying attacks. Microsoft says defenders can look for rapid, varied requests and default tool traffic, while noting that attackers can quickly change those characteristics. It recommends decoys, honeypots, tarpits, and fake wins; in Microsoft testing, these reduced traffic reaching real assets and yielded high-confidence signals. Microsoft also describes risk detections in Entra ID Protection, endpoint alerts and IOCs in Defender for Endpoint, cross-domain investigation in Defender, and hunting queries for curl downloads and listed IP indicators. Detection coverage depends on the activity source and products deployed; listed indicators can be evaded through proxies or VPNs.

### Source excerpt

In October 2026, the financially motivated threat actor Storm-3358 began targeting organizations in the financial sector using the agentic AI offensive framework ARTEX. The post ARTEX abuse expands as cybercriminals target financial sector appeared first on Microsoft Security Blog.

## Threat actors use agentic AI tooling to find and abuse exposed secrets

DevFeed: [Threat actors use agentic AI tooling to find and abuse exposed secrets](<https://devfeed.tech/articles/threat-actors-use-agentic-ai-tooling-to-find-and-abuse-exposed-secrets-120855.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/11/05/threat-actors-use-agentic-ai-tooling-to-find-and-abuse-exposed-secrets/>)

Author: Microsoft Threat Intelligence and Microsoft Security Research

Published: 2026-11-05T23:46:50Z

Content type: news

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Secret Scanning](<https://devfeed.tech/topics/secret-scanning.md>), [Secrets Management](<https://devfeed.tech/topics/secrets-management.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Threat monitoring](<https://devfeed.tech/topics/threat-monitoring.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [application](<https://devfeed.tech/tags/application.md>), [applications](<https://devfeed.tech/tags/applications.md>), [artex](<https://devfeed.tech/tags/artex.md>), [blog](<https://devfeed.tech/tags/blog.md>), [can](<https://devfeed.tech/tags/can.md>), [compromise](<https://devfeed.tech/tags/compromise.md>), [credential-theft](<https://devfeed.tech/tags/credential-theft.md>), [exposed](<https://devfeed.tech/tags/exposed.md>), [first](<https://devfeed.tech/tags/first.md>), [framework](<https://devfeed.tech/tags/framework.md>), [github](<https://devfeed.tech/tags/github.md>), [intelligence](<https://devfeed.tech/tags/intelligence.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [oauth](<https://devfeed.tech/tags/oauth.md>), [secrets](<https://devfeed.tech/tags/secrets.md>), [tooling](<https://devfeed.tech/tags/tooling.md>)

### AI overview

Microsoft reports threat actors using the ARTEX agentic offensive framework to scan public GitHub repositories for exposed credentials and then pursue cloud resources. In one observed case, an agent moved from searching for OAuth client secrets to exfiltrating Azure Key Vault data in five minutes. Follow-on activity included Entra service principal sign-ins, cloud resource discovery, credential and data access, and attempts to use Azure AI services. Microsoft says exposed credentials should be treated as compromised even if the code is later removed: revoke or rotate them, investigate historical use, review sign-in and cloud audit logs, and restrict application permissions. Recommended defenses include scanning repositories, enabling secret scanning and push protection, using managed identities where supported, applying least privilege, and protecting critical workloads. The text also describes honeypots, decoys, and tarpits as ways to divert agentic attacks, while warning that attackers can change IPs and other fingerprints. Several incident details and dates are tied to Microsoft's observations and may not represent all activity.

### Source excerpt

Microsoft Threat Intelligence has observed threat actors using the agentic offensive security framework ARTEX to search GitHub for OAuth application secrets, which can be used to compromise the associated OAuth application and perform authenticated actions in the application's tenant. Agents operating on behalf of threat actors then used the compromised OAuth applications to perform a variety of subsequent actions within compromised organizations. The post Threat actors use agentic AI tooling to find and abuse exposed secrets appeared first on Microsoft Security Blog.

## New investments to reduce on-premises security risk

DevFeed: [New investments to reduce on-premises security risk](<https://devfeed.tech/articles/new-investments-to-reduce-on-premises-security-risk-120853.md>)

Original publisher: [Read original article](<https://techcommunity.microsoft.com/blog/microsoft-security-blog/new-investments-to-reduce-on-premises-security-risk/4570381>)

Author: Paul Lorimer

Published: 2026-11-05T17:10:14Z

Content type: release

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [Security](<https://devfeed.tech/topics/security.md>), [known exploitable vulnerabilities](<https://devfeed.tech/topics/known-exploitable-vulnerabilities.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [act](<https://devfeed.tech/tags/act.md>), [actions](<https://devfeed.tech/tags/actions.md>), [adapting](<https://devfeed.tech/tags/adapting.md>), [administrator](<https://devfeed.tech/tags/administrator.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-readiness](<https://devfeed.tech/tags/ai-readiness.md>), [also](<https://devfeed.tech/tags/also.md>), [analyze](<https://devfeed.tech/tags/analyze.md>), [application](<https://devfeed.tech/tags/application.md>), [apply](<https://devfeed.tech/tags/apply.md>), [approach](<https://devfeed.tech/tags/approach.md>), [guidance](<https://devfeed.tech/tags/guidance.md>), [initiative](<https://devfeed.tech/tags/initiative.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [migration](<https://devfeed.tech/tags/migration.md>), [product](<https://devfeed.tech/tags/product.md>), [reduce](<https://devfeed.tech/tags/reduce.md>), [risk](<https://devfeed.tech/tags/risk.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

Microsoft's on-premises security initiative combines guidance, migration, and product changes, initially for server workloads. It recommends moving workloads to Microsoft 365 where possible and, for those that remain, using supported releases, applying current updates, assessing exposure, and enabling available protections. On-Premises Baseline Security Mode aims to make supported Exchange Server, SharePoint Server, and Skype for Business Server deployments more secure by default while preserving administrator control. The plans cover faster patching, hardened defaults and configuration-drift identification, and Emergency Mitigation Service protections for emerging vulnerabilities. Timing is qualified: automatic updates for connected environments are targeted for Q1 2027; hardened defaults and drift identification are planned for Q1 2027; Emergency Mitigation Service 2.0 is planned for Exchange and Skype for Business in December 2026 and SharePoint in January 2027. Interim mitigations reduce immediate exposure but do not replace security updates.

### Source excerpt

We're announcing a new on-premises security initiative, bringing together guidance, migration, and product investments. The post New investments to reduce on-premises security risk appeared first on Microsoft Security Blog.

## Email threat landscape: Q3 2026 trends and insights

DevFeed: [Email threat landscape: Q3 2026 trends and insights](<https://devfeed.tech/articles/email-threat-landscape-q3-2026-trends-and-insights-120854.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/11/05/email-threat-landscape-q3-2026-trends-and-insights/>)

Author: Microsoft Threat Intelligence and Microsoft Defender Security Research Team

Published: 2026-11-05T16:00:00Z

Content type: article

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [email](<https://devfeed.tech/topics/email.md>), [Threat Research](<https://devfeed.tech/topics/threat-research.md>), [Threat monitoring](<https://devfeed.tech/topics/threat-monitoring.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Threat Hunting & Intel](<https://devfeed.tech/topics/threat-hunting-intel.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [based](<https://devfeed.tech/tags/based.md>), [blog](<https://devfeed.tech/tags/blog.md>), [business](<https://devfeed.tech/tags/business.md>), [captcha](<https://devfeed.tech/tags/captcha.md>), [code](<https://devfeed.tech/tags/code.md>), [credential-theft](<https://devfeed.tech/tags/credential-theft.md>), [domains](<https://devfeed.tech/tags/domains.md>), [email](<https://devfeed.tech/tags/email.md>), [exposed](<https://devfeed.tech/tags/exposed.md>), [first](<https://devfeed.tech/tags/first.md>), [insights](<https://devfeed.tech/tags/insights.md>), [intelligence](<https://devfeed.tech/tags/intelligence.md>), [malicious](<https://devfeed.tech/tags/malicious.md>), [malware](<https://devfeed.tech/tags/malware.md>), [messages](<https://devfeed.tech/tags/messages.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [phishing](<https://devfeed.tech/tags/phishing.md>), [q3](<https://devfeed.tech/tags/q3.md>), [qr-code](<https://devfeed.tech/tags/qr-code.md>), [security](<https://devfeed.tech/tags/security.md>), [social-engineering](<https://devfeed.tech/tags/social-engineering.md>), [trends](<https://devfeed.tech/tags/trends.md>), [vishing](<https://devfeed.tech/tags/vishing.md>)

### AI overview

Microsoft detected about 7.3 billion email phishing threats in Q3 2026, with September volume rising 41% from August. Techniques shifted: QR code phishing fell 67% from Q2, while CAPTCHA-gated attacks recovered, partly through increased use of SVG attachments. Credential theft remained the dominant payload objective. A key exposure was sender-domain spoofing: about 129 million malicious messages imitated tracked business services, and September security overrides applied to 63% of messages with a recorded outcome, despite failed authentication and malicious classification. The excerpt does not establish that recipients opened these messages or that accounts were compromised. Teams call attempts and business contact impersonation also featured, alongside campaigns using a personalized QR code for device-code phishing and disguised archives to deliver Agent Tesla. Microsoft recommends reviewing security exceptions and layered email and Teams protections, including Safe Links and Safe Attachments, ZAP, user training, and phishing-resistant authentication for privileged accounts.

### Source excerpt

Microsoft Threat Intelligence observed a sharp rise in email-based phishing activity at the end of Q3 2026 (July - September), even as QR code phishing declined, CAPTCHA-gated phishing recovered, and malicious messages spoofing familiar business-service sender domains exposed risks associated with security overrides. The post Email threat landscape: Q3 2026 trends and insights appeared first on Microsoft Security Blog.

## Fake-download campaign uses trojanized installers to deliver monetization payloads

DevFeed: [Fake-download campaign uses trojanized installers to deliver monetization payloads](<https://devfeed.tech/articles/fake-download-campaign-uses-trojanized-installers-to-deliver-monetization-payloads-115927.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/11/03/fake-download-campaign-uses-trojanized-installers-deliver-monetization-payloads/>)

Author: Microsoft Security Research and Jiacen Xu

Published: 2026-11-03T17:32:47Z

Content type: news

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [infection chain](<https://devfeed.tech/topics/infection-chain.md>), [Endpoint Security & XDR](<https://devfeed.tech/topics/endpoint-security-xdr.md>), [Endpoint security](<https://devfeed.tech/topics/endpoint-security.md>), [Threat monitoring](<https://devfeed.tech/topics/threat-monitoring.md>)

Tags: [blog](<https://devfeed.tech/tags/blog.md>), [campaign](<https://devfeed.tech/tags/campaign.md>), [complete](<https://devfeed.tech/tags/complete.md>), [detection](<https://devfeed.tech/tags/detection.md>), [download](<https://devfeed.tech/tags/download.md>), [fake](<https://devfeed.tech/tags/fake.md>), [first](<https://devfeed.tech/tags/first.md>), [guidance](<https://devfeed.tech/tags/guidance.md>), [installer](<https://devfeed.tech/tags/installer.md>), [intelligence](<https://devfeed.tech/tags/intelligence.md>), [investigation](<https://devfeed.tech/tags/investigation.md>), [malware](<https://devfeed.tech/tags/malware.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [monetization](<https://devfeed.tech/tags/monetization.md>), [multiple](<https://devfeed.tech/tags/multiple.md>), [offers](<https://devfeed.tech/tags/offers.md>), [provides](<https://devfeed.tech/tags/provides.md>), [security](<https://devfeed.tech/tags/security.md>), [security-blog](<https://devfeed.tech/tags/security-blog.md>), [threat-intelligence](<https://devfeed.tech/tags/threat-intelligence.md>), [uses](<https://devfeed.tech/tags/uses.md>)

### AI overview

Microsoft Threat Intelligence describes a fake-download campaign targeting users seeking cracked software, games, activators, plugins, and unofficial utilities. Trojanized Inno-style installers stage executables in temporary directories and use per-offer callbacks to coordinate payload delivery; offers can succeed or fail independently, and callback domains rotate. Investigators confirmed three monetization branches: WorldProxyPool uses device network resources and creates recurring SYSTEM scheduled tasks; CharityEngine and BOINC use compute resources; and AW Manager or Windows Manager installs utility-style software, often without informed consent. The report recommends avoiding untrusted downloads, enabling Microsoft Defender protections, and investigating Inno temporary execution, callback patterns, unexpected scheduled tasks, and unrequested software. It also provides Defender XDR hunting queries, detections, IOCs, and MITRE ATT&CK mappings. Callback matches and domains are leads that should be correlated with endpoint activity; a failed offer does not establish that the bundle stopped.

### Source excerpt

Microsoft Threat Intelligence tracks a fake-download campaign that uses trojanized Inno installers to deliver multiple monetization offers and provides detection and investigation guidance across the complete installer session. The post Fake-download campaign uses trojanized installers to deliver monetization payloads appeared first on Microsoft Security Blog.

## Microsoft named a Leader in the 2026 Gartner® Magic Quadrant™ for AI Agent Management Platforms

DevFeed: [Microsoft named a Leader in the 2026 Gartner® Magic Quadrant™ for AI Agent Management Platforms](<https://devfeed.tech/articles/microsoft-named-a-leader-in-the-2026-gartner-magic-quadranttm-for-ai-agent-management-platforms-115928.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/11/03/microsoft-named-a-leader-in-the-2026-gartner-magic-quadrant-for-ai-agent-management-platforms/>)

Author: Nadim Abdo and Ray Smith

Published: 2026-11-03T17:00:00Z

Content type: article

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [identity and access management](<https://devfeed.tech/topics/identity-and-access-management.md>), [Endpoint security](<https://devfeed.tech/topics/endpoint-security.md>), [Purview](<https://devfeed.tech/topics/purview.md>), [Microsoft](<https://devfeed.tech/topics/microsoft.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-management](<https://devfeed.tech/tags/agent-management.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-management](<https://devfeed.tech/tags/ai-agent-management.md>), [gartner](<https://devfeed.tech/tags/gartner.md>), [gartner-magic-quadrant](<https://devfeed.tech/tags/gartner-magic-quadrant.md>), [gartner-magic-quadranttm](<https://devfeed.tech/tags/gartner-magic-quadranttm.md>), [leader](<https://devfeed.tech/tags/leader.md>), [microsoft-agent-365](<https://devfeed.tech/tags/microsoft-agent-365.md>)

### AI overview

Microsoft says Gartner named it a Leader in the inaugural 2026 Magic Quadrant for AI Agent Management Platforms, and presents Agent 365 as a way to govern agents using identity controls and existing Microsoft security and administration tools. Microsoft Entra Agent ID assigns each agent an ID, owner and purpose, with access adjusted as risk signals change. Agent 365's registry combines supported Microsoft and customer-built agents, device discoveries and integrations with partner platforms including Agentforce, Amazon Bedrock, Anthropic, Databricks, Google Gemini and Google Vertex; further integrations and cloud-agent discovery are described as planned or in preview. Microsoft says it has registered more than 50 million agents and plans to expand local-agent discovery to 60 types, extend controls to unmanaged and third-party agents, and use the Agent 365 Action Center for suggested or automated governance actions. The article also notes ongoing work on cost, task classification and value measurement. Gartner's disclaimer says its publications express opinions and do not endorse vendors or products.

### Source excerpt

Read why Gartner named Microsoft a Leader in the inaugural 2026 Magic Quadrant for AI Agent Management Platforms. The post Microsoft named a Leader in the 2026 Gartner® Magic Quadrant™ for AI Agent Management Platforms appeared first on Microsoft Security Blog.

## What exploited vulnerabilities have in common: A data-driven analysis of real-world attacks

DevFeed: [What exploited vulnerabilities have in common: A data-driven analysis of real-world attacks](<https://devfeed.tech/articles/what-exploited-vulnerabilities-have-in-common-a-data-driven-analysis-of-real-world-attacks-113122.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/11/02/exploited-vulnerabilities-common-data-driven-analysis-real-world-attacks/>)

Author: Microsoft Security Research, Yair Tsarfaty and Or Begam

Published: 2026-11-02T20:20:59Z

Content type: article

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [known exploitable vulnerabilities](<https://devfeed.tech/topics/known-exploitable-vulnerabilities.md>), [Exposure Management](<https://devfeed.tech/topics/exposure-management.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [Security research](<https://devfeed.tech/topics/security-research.md>)

Tags: [access-controls](<https://devfeed.tech/tags/access-controls.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [asset](<https://devfeed.tech/tags/asset.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [blast-radius](<https://devfeed.tech/tags/blast-radius.md>), [cves](<https://devfeed.tech/tags/cves.md>), [data](<https://devfeed.tech/tags/data.md>), [data-driven](<https://devfeed.tech/tags/data-driven.md>), [exploitation](<https://devfeed.tech/tags/exploitation.md>), [exploited](<https://devfeed.tech/tags/exploited.md>), [exploited-vulnerabilities](<https://devfeed.tech/tags/exploited-vulnerabilities.md>), [impact](<https://devfeed.tech/tags/impact.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [real-world](<https://devfeed.tech/tags/real-world.md>), [security](<https://devfeed.tech/tags/security.md>), [security-blog](<https://devfeed.tech/tags/security-blog.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>), [world](<https://devfeed.tech/tags/world.md>)

### AI overview

The analysis reports that only about 0.5% of roughly 383,000 disclosed CVEs through September 2026 were linked to real-world exploitation, and that 78% of exploited vulnerabilities enable takeover, such as remote code execution, authentication bypass, or local privilege escalation. Exploited CVEs are more concentrated in server-side RCE, privilege escalation, client-side RCE, and OS flaws than the overall CVE population; the text cautions that a stated vulnerability classification may overstate what attackers can achieve in practice. Because exploitation can begin quickly while patching critical systems takes weeks or longer, it recommends prioritizing by impact, exposure, asset criticality, and blast radius. Microsoft Defender External Attack Surface Management finds reachable assets; Defender Vulnerability Management uses threat and exposure signals to prioritize remediation; Attack Path Analysis maps routes to critical assets across endpoints, cloud, and hybrid environments, with Defender CSPM adding cloud context across Azure, AWS, and Google Cloud. The text also flags denial of service on availability-critical assets and credential or secret disclosure as context-dependent.

### Source excerpt

Real-world exploitation concentrates in a small, high-impact subset of CVEs. Learn how defenders can prioritize vulnerabilities based on exploitation likelihood, exposure, and potential blast radius. The post What exploited vulnerabilities have in common: A data-driven analysis of real-world attacks appeared first on Microsoft Security Blog.

## Inside a malicious Claude Code-branded extension and its persistent SSH backdoor

DevFeed: [Inside a malicious Claude Code-branded extension and its persistent SSH backdoor](<https://devfeed.tech/articles/inside-a-malicious-claude-code-branded-extension-and-its-persistent-ssh-backdoor-109876.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/10/30/inside-malicious-claude-code-branded-cursor-extension-persistent-ssh-backdoor/>)

Author: Microsoft Security Research

Published: 2026-10-31T01:02:57Z

Content type: news

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [software supply-chain attack](<https://devfeed.tech/topics/software-supply-chain-attack.md>), [ssh](<https://devfeed.tech/topics/ssh.md>), [OpenSSH](<https://devfeed.tech/topics/openssh.md>), [malware protection](<https://devfeed.tech/topics/malware-protection.md>), [VS Code Extension](<https://devfeed.tech/topics/vscode-extension.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>)

Tags: [backdoor](<https://devfeed.tech/tags/backdoor.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [extension](<https://devfeed.tech/tags/extension.md>), [frontier-ai-models](<https://devfeed.tech/tags/frontier-ai-models.md>), [malicious](<https://devfeed.tech/tags/malicious.md>), [security](<https://devfeed.tech/tags/security.md>), [ssh](<https://devfeed.tech/tags/ssh.md>), [supply-chain-attack](<https://devfeed.tech/tags/supply-chain-attack.md>)

### AI overview

Microsoft's analysis says a tampered Claude Code extension (versions 2.1.312 and 2.1.313) was available in Cursor's marketplace for several hours; the evidence described points to Cursor, while Microsoft's Visual Studio Marketplace, npm, and Anthropic systems were not affected. Its injected JavaScript collected host details, attempted to add an SSH authorization key, open outbound reverse SSH forwarding to local port 22, establish platform-specific startup persistence, and later report host details plus matching environment-variable names--not their values. Successful access depended on host privileges and SSH configuration, and attempted steps could leave artifacts even when tunneling failed. The excerpt recommends identifying affected installs, preserving evidence, reviewing endpoint, network, and authentication telemetry, then removing verified keys, scripts, identities, and startup entries separately. It also gives platform-specific artifact locations and Defender XDR hunting queries, whose matches are investigative leads rather than proof of compromise.

### Source excerpt

Microsoft analyzes a malicious Claude Code-branded extension, its persistent SSH backdoor, and guidance to detect and remediate it. The post Inside a malicious Claude Code-branded extension and its persistent SSH backdoor appeared first on Microsoft Security Blog.

## From help desk impersonation to AD CS abuse: Investigating ESC1 and ESC8 intrusion paths

DevFeed: [From help desk impersonation to AD CS abuse: Investigating ESC1 and ESC8 intrusion paths](<https://devfeed.tech/articles/from-help-desk-impersonation-to-ad-cs-abuse-investigating-esc1-and-esc8-intrusion-paths-109510.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/10/30/help-desk-impersonation-ad-cs-abuse-investigating-esc1-esc8-intrusion-paths/>)

Author: Microsoft Security Research, Sagar Patil, Jesse Birch and Tal Tzhori

Published: 2026-10-30T16:11:44Z

Content type: news

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [Security](<https://devfeed.tech/topics/security.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Access Control](<https://devfeed.tech/topics/access-control.md>), [network security](<https://devfeed.tech/topics/network-security.md>), [Security research](<https://devfeed.tech/topics/security-research.md>), [Security Information and Event Management (SIEM)](<https://devfeed.tech/topics/siem-security.md>), [microsoft 365](<https://devfeed.tech/topics/microsoft-365.md>)

Tags: [active-directory](<https://devfeed.tech/tags/active-directory.md>), [attack](<https://devfeed.tech/tags/attack.md>), [attack-disruption](<https://devfeed.tech/tags/attack-disruption.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [bun](<https://devfeed.tech/tags/bun.md>), [certificate](<https://devfeed.tech/tags/certificate.md>), [execution](<https://devfeed.tech/tags/execution.md>), [help-desk](<https://devfeed.tech/tags/help-desk.md>), [impersonation](<https://devfeed.tech/tags/impersonation.md>), [kerberos](<https://devfeed.tech/tags/kerberos.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [relay](<https://devfeed.tech/tags/relay.md>), [remote](<https://devfeed.tech/tags/remote.md>), [remote-access](<https://devfeed.tech/tags/remote-access.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [security](<https://devfeed.tech/tags/security.md>), [services](<https://devfeed.tech/tags/services.md>), [support](<https://devfeed.tech/tags/support.md>), [teams](<https://devfeed.tech/tags/teams.md>)

### AI overview

Two investigated intrusions began with Teams help desk impersonation and user-approved Quick Assist access, then staged portable runtimes and probed Active Directory Certificate Services (AD CS). They diverged at the certificate layer: one abused an ESC1 template to obtain privileged-account certificates and perform DCSync; the other used PetitPotam to coerce a domain controller's NTLM authentication, relayed it to AD CS Web Enrollment (ESC8), and used the issued machine certificate for Kerberos PKINIT. In the first case, Defender disruption blocked substantial follow-on activity, but an excluded privileged identity remained usable and supported data exfiltration. In the second, the customer isolated the workstation after ESC8 alerts, and no further progression was observed. The text recommends correlating Teams and remote-session records, endpoint process lineage, certificate requests and issuance, and Kerberos activity; hardening templates and enrollment endpoints against ESC1 and NTLM relay; auditing certificate issuance; and treating certificate revocation and existing Kerberos tickets as separate response tasks. The activity is not attributed to a specific actor.

### Source excerpt

Teams support impersonation led to remote access, malicious runtime execution, and Certificate Services abuse through authentication relay and Kerberos. The post From help desk impersonation to AD CS abuse: Investigating ESC1 and ESC8 intrusion paths appeared first on Microsoft Security Blog.

## IDC MarketScape names Microsoft a Leader in the 2026 Worldwide Modern Endpoint Security for Enterprises Vendor Assessment

DevFeed: [IDC MarketScape names Microsoft a Leader in the 2026 Worldwide Modern Endpoint Security for Enterprises Vendor Assessment](<https://devfeed.tech/articles/idc-marketscape-names-microsoft-a-leader-in-the-2026-worldwide-modern-endpoint-security-for-enterprises-vendor-assessment-107758.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/10/29/idc-marketscape-names-microsoft-a-leader-in-the-2026-worldwide-modern-endpoint-security-for-enterprises-vendor-assessment/>)

Author: Rob Lefferts

Published: 2026-10-29T16:00:00Z

Content type: release

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [Endpoint security](<https://devfeed.tech/topics/endpoint-security.md>), [Endpoint Security & XDR](<https://devfeed.tech/topics/endpoint-security-xdr.md>), [Security](<https://devfeed.tech/topics/security.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [alert triage](<https://devfeed.tech/topics/alert-triage.md>), [credential-based attacks](<https://devfeed.tech/topics/credential-based-attacks.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [assessment](<https://devfeed.tech/tags/assessment.md>), [endpoint-security](<https://devfeed.tech/tags/endpoint-security.md>), [enterprises](<https://devfeed.tech/tags/enterprises.md>), [idc](<https://devfeed.tech/tags/idc.md>), [leader](<https://devfeed.tech/tags/leader.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [modern](<https://devfeed.tech/tags/modern.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

Microsoft says IDC named it a Leader in the 2026 Worldwide Modern Endpoint Security for Enterprises MarketScape. The excerpt highlights Defender's AI-driven attack disruption, which correlates signals across endpoints, identities, email and cloud to contain compromised devices and users; it cites a QNET incident stopped within 128 seconds of a high-severity alert. It also describes agentic AI as generally available with measured gains in alert accuracy and analyst time saved. For local AI agents, discovery is available on Windows and macOS for more than 50 supported agents and MCP servers; runtime protection against malicious instructions is in preview on Windows. Microsoft also cites sovereign cloud and data residency options for regulated and multinational customers. These are capabilities and results reported in Microsoft's post; the excerpt does not provide comparative vendor results.

### Source excerpt

IDC has named Microsoft a Leader in the 2026 IDC MarketScape for Worldwide Modern Endpoint Security for Enterprises. The post IDC MarketScape names Microsoft a Leader in the 2026 Worldwide Modern Endpoint Security for Enterprises Vendor Assessment appeared first on Microsoft Security Blog.

## Tracking AI adoption in North Korean threat actor tradecraft

DevFeed: [Tracking AI adoption in North Korean threat actor tradecraft](<https://devfeed.tech/articles/tracking-ai-adoption-in-north-korean-threat-actor-tradecraft-107759.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/10/29/tracking-ai-adoption-in-north-korean-threat-actor-tradecraft/>)

Author: Microsoft Threat Intelligence

Published: 2026-10-29T16:00:00Z

Content type: article

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [ai-assisted attacks](<https://devfeed.tech/topics/ai-assisted-attacks.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Threat Hunting & Intel](<https://devfeed.tech/topics/threat-hunting-intel.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [vulnerability management](<https://devfeed.tech/topics/vulnerability-management.md>)

Tags: [2023](<https://devfeed.tech/tags/2023.md>), [actor](<https://devfeed.tech/tags/actor.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-adoption](<https://devfeed.tech/tags/ai-adoption.md>), [attack](<https://devfeed.tech/tags/attack.md>), [attack-chains](<https://devfeed.tech/tags/attack-chains.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [blog](<https://devfeed.tech/tags/blog.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [intelligence](<https://devfeed.tech/tags/intelligence.md>), [korean](<https://devfeed.tech/tags/korean.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [net](<https://devfeed.tech/tags/net.md>), [north](<https://devfeed.tech/tags/north.md>), [operations](<https://devfeed.tech/tags/operations.md>), [sapphire-sleet](<https://devfeed.tech/tags/sapphire-sleet.md>), [security](<https://devfeed.tech/tags/security.md>), [sleet](<https://devfeed.tech/tags/sleet.md>), [social-engineering](<https://devfeed.tech/tags/social-engineering.md>), [speed](<https://devfeed.tech/tags/speed.md>), [threat-intelligence](<https://devfeed.tech/tags/threat-intelligence.md>), [tracking](<https://devfeed.tech/tags/tracking.md>)

### AI overview

Microsoft assesses North Korean threat actors' AI adoption as high but uneven: Jade Sleet, Coral Sleet, and Jasper Sleet have operationalized AI across workflows; Diamond, Onyx, Pearl, and Sapphire Sleet are accelerating adoption; Emerald Sleet is expanding use. Reported applications include reconnaissance, tailored job lures and fabricated identities, code and malware development, and scaling repetitive tasks. Examples include Onyx Sleet generating dozens of tailored PDF lures within minutes and Onyx and Pearl Sleet using the ARTEX agentic penetration-testing framework. Microsoft says these operations remain human-directed, with AI enhancing established tradecraft and objectives rather than changing them. The article recommends vulnerability and exposure management, phishing defenses and user training, scrutiny of prospective employees, and malware protections; it also describes Microsoft security dashboards, agent controls, and Defender detections. These are Microsoft's assessments and guidance in the supplied text.

### Source excerpt

As Microsoft Threat Intelligence continues to track how threat actors operationalize AI to increase the speed and efficiency of attacks, we've identified North Korean threat actors expanding their use of AI with varying levels of adoption. This blog breaks down how North Korean threat actors are utilizing AI across their operations, reflecting a broader trend of threat actors incorporating AI into their attack chains. The post Tracking AI adoption in North Korean threat actor tradecraft appeared first on Microsoft Security Blog.

## The CISO's evolving role: Protecting and defending in the agentic era

DevFeed: [The CISO's evolving role: Protecting and defending in the agentic era](<https://devfeed.tech/articles/the-ciso-s-evolving-role-protecting-and-defending-in-the-agentic-era-106308.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/10/28/the-cisos-evolving-role-protecting-and-defending-in-the-agentic-era/>)

Author: Aarti Borkar

Published: 2026-10-28T16:00:00Z

Content type: article

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [ai security](<https://devfeed.tech/topics/ai-security.md>), [Cybersecurity](<https://devfeed.tech/topics/cybersecurity.md>), [Agentic SOC](<https://devfeed.tech/topics/agentic-soc.md>), [enterprise data protection](<https://devfeed.tech/topics/enterprise-data-protection.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [adopting](<https://devfeed.tech/tags/adopting.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-powered](<https://devfeed.tech/tags/ai-powered.md>), [ciso](<https://devfeed.tech/tags/ciso.md>), [ciso-s](<https://devfeed.tech/tags/ciso-s.md>), [critical](<https://devfeed.tech/tags/critical.md>), [data](<https://devfeed.tech/tags/data.md>), [defense](<https://devfeed.tech/tags/defense.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [era](<https://devfeed.tech/tags/era.md>), [guardrails](<https://devfeed.tech/tags/guardrails.md>), [identity](<https://devfeed.tech/tags/identity.md>), [innovation](<https://devfeed.tech/tags/innovation.md>), [modernizing](<https://devfeed.tech/tags/modernizing.md>), [security](<https://devfeed.tech/tags/security.md>), [threats](<https://devfeed.tech/tags/threats.md>)

### AI overview

The article frames CISOs' work in the agentic era as enabling governed AI use while adapting defense to AI-accelerated threats. For builders, it recommends assigning agents governed identities where supported and appropriate, protecting the data they can access, and involving security teams early. For CISOs, it emphasizes visibility into agents, their owners, permissions, and behavior, alongside least-privilege identities and classified, protected data. On defense, it calls for integrating signals across identity, endpoints, applications, and cloud with threat intelligence and organizational context, supported by partners and agents that help analysts investigate and respond. These are the author's recommendations; the excerpt provides no comparative evaluation of specific tools.

### Source excerpt

As AI and agents reshape the enterprise, CISOs face two critical priorities: enabling innovation with the right identity and data guardrails, and modernizing defense to keep pace with AI-powered threats. Aarti Borkar shares how security leaders can approach both. The post The CISO's evolving role: Protecting and defending in the agentic era appeared first on Microsoft Security Blog.

## Inside the LiteLLM 1.107.0 supply chain compromise: Credential theft through Python startup hooks

DevFeed: [Inside the LiteLLM 1.107.0 supply chain compromise: Credential theft through Python startup hooks](<https://devfeed.tech/articles/inside-the-litellm-1-107-0-supply-chain-compromise-credential-theft-through-python-startup-hooks-98535.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/10/23/inside-the-litellm-1-107-0-supply-chain-compromise-credential-theft-through-python-startup-hooks/>)

Author: Microsoft Security Research, Mahesh Mandava, Srinivasan Govindarajan, Sagar Patil and Suriyaraj Natarajan

Published: 2026-10-23T18:12:19Z

Content type: news

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [litellm attack](<https://devfeed.tech/topics/litellm-attack.md>), [Credential theft](<https://devfeed.tech/topics/credential-theft.md>), [software supply-chain attack](<https://devfeed.tech/topics/software-supply-chain-attack.md>), [litellm](<https://devfeed.tech/topics/litellm.md>), [malicious packages](<https://devfeed.tech/topics/malicious-packages.md>), [supply-chain-security](<https://devfeed.tech/topics/supply-chain-security.md>), [Endpoint security](<https://devfeed.tech/topics/endpoint-security.md>), [Threat monitoring](<https://devfeed.tech/topics/threat-monitoring.md>), [hooks](<https://devfeed.tech/topics/hooks.md>), [credential-based attacks](<https://devfeed.tech/topics/credential-based-attacks.md>), [import](<https://devfeed.tech/topics/import.md>), [AI software supply chain security](<https://devfeed.tech/topics/ai-software-supply-chain-security.md>)

Tags: [compromise](<https://devfeed.tech/tags/compromise.md>), [credential-theft](<https://devfeed.tech/tags/credential-theft.md>), [hooks](<https://devfeed.tech/tags/hooks.md>), [litellm](<https://devfeed.tech/tags/litellm.md>), [python](<https://devfeed.tech/tags/python.md>), [startup](<https://devfeed.tech/tags/startup.md>), [supply-chain](<https://devfeed.tech/tags/supply-chain.md>), [supply-chain-attack](<https://devfeed.tech/tags/supply-chain-attack.md>), [supply-chain-compromise](<https://devfeed.tech/tags/supply-chain-compromise.md>)

### AI overview

LiteLLM 1.107.0 carried Python startup files that could launch credential theft whenever Python started in an affected environment, even if an application never imported LiteLLM. The recovered collector gathered accessible developer, cloud, browser, infrastructure, and LiteLLM proxy data, encrypted it, and attempted to send it to an attacker-controlled endpoint. A separate Unix-oriented loader could retrieve and execute more Python code, but Microsoft did not confirm that second-stage activity. The excerpt says package presence alone does not prove collection or compromise, and deleting the LiteLLM directory may leave startup files behind. Response guidance includes isolating affected systems, avoiding Python or pip there during investigation, rebuilding from verified artifacts, rotating reachable credentials from a clean machine, and correlating hashes, process, network, and identity evidence. Microsoft also provides Defender detections and hunting queries, which are investigation leads rather than standalone verdicts.

### Source excerpt

Microsoft Threat Intelligence analyzes the LiteLLM 1.107.0 compromise, including Python startup hooks, credential theft, remote code loading, detections, and mitigations. The post Inside the LiteLLM 1.107.0 supply chain compromise: Credential theft through Python startup hooks appeared first on Microsoft Security Blog.

## AI-driven, large-scale nation-state campaign using ARTEX enables supply chain compromise

DevFeed: [AI-driven, large-scale nation-state campaign using ARTEX enables supply chain compromise](<https://devfeed.tech/articles/ai-driven-large-scale-nation-state-campaign-using-artex-enables-supply-chain-compromise-93105.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/10/21/storm-0940-uses-artex-agentic-ai-connectwise-supply-chain-compromise/>)

Author: Microsoft Security Research and Microsoft Threat Intelligence

Published: 2026-10-21T18:23:55Z

Content type: news

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [software supply-chain attack](<https://devfeed.tech/topics/software-supply-chain-attack.md>), [AI in cybersecurity](<https://devfeed.tech/topics/ai-in-cybersecurity.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [artex](<https://devfeed.tech/tags/artex.md>), [campaign](<https://devfeed.tech/tags/campaign.md>), [state](<https://devfeed.tech/tags/state.md>), [supply-chain](<https://devfeed.tech/tags/supply-chain.md>), [supply-chain-attack](<https://devfeed.tech/tags/supply-chain-attack.md>), [supply-chain-compromise](<https://devfeed.tech/tags/supply-chain-compromise.md>)

### AI overview

Microsoft attributes the ConnectWise multi-tenant application compromise to Storm-0940, which used ARTEX, an autonomous, multi-agent penetration testing framework, to accelerate scanning, password spraying and OAuth application abuse. The campaign reached more than 2,250 tenants at 2,900 sign-in attempts per minute; some attacks obtained privileged cloud access in under three hours. Microsoft observed follow-on Microsoft Graph reconnaissance and attempts to change application credentials and privileges. A separate password-spray campaign generated over 151,000 failed logons across eight organizations, with no successful authentication or Graph activity observed in that campaign. Affected application presence or successful sign-in alone does not establish data access or exfiltration. Microsoft advises reviewing service-principal sign-ins, Graph and directory changes, preserving logs and evidence, keeping affected ConnectWise connections disabled pending restoration guidance, and removing confirmed unauthorized access. Defender XDR detections and hunting queries are provided.

### Source excerpt

Storm-0940 used ARTEX agentic AI to accelerate a ConnectWise supply chain compromise, enabling application credential abuse across Microsoft 365 environments. The post AI-driven, large-scale nation-state campaign using ARTEX enables supply chain compromise appeared first on Microsoft Security Blog.

## Agents are your newest insiders. Security must move at their speed.

DevFeed: [Agents are your newest insiders. Security must move at their speed.](<https://devfeed.tech/articles/agents-are-your-newest-insiders-security-must-move-at-their-speed-90253.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/10/19/agents-are-your-newest-insiders-security-must-move-at-their-speed/>)

Author: Nadim Abdo

Published: 2026-10-19T13:00:00Z

Content type: article

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [LLM security](<https://devfeed.tech/topics/llm-security.md>), [least privilege](<https://devfeed.tech/topics/least-privilege.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [agent to agent communication](<https://devfeed.tech/topics/agent-to-agent-communication.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [api](<https://devfeed.tech/tags/api.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [authorization](<https://devfeed.tech/tags/authorization.md>), [context](<https://devfeed.tech/tags/context.md>), [control](<https://devfeed.tech/tags/control.md>), [security](<https://devfeed.tech/tags/security.md>), [speed](<https://devfeed.tech/tags/speed.md>)

### AI overview

Microsoft describes how organizations can secure AI agents by assigning them distinct identities, limiting their permissions, monitoring changing risks, and adapting protections continuously. The post introduces Project Perception capabilities, including Dynamic Permissions, Dynamic Agent Risk, Dynamic Conditional Access, and Guardian Agents, while emphasizing that independent controls and human-defined policies should govern agent actions.

### Source excerpt

New capabilities in Microsoft 365 E7 and Project Perception help organizations contain agent risk and adapt protection continuously. The post Agents are your newest insiders. Security must move at their speed. appeared first on Microsoft Security Blog.

## Managing open-weight model risk in enterprise deployments

DevFeed: [Managing open-weight model risk in enterprise deployments](<https://devfeed.tech/articles/managing-open-weight-model-risk-in-enterprise-deployments-88751.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/10/16/managing-open-weight-model-risk-in-enterprise-deployments/>)

Author: Michael Scovetta

Published: 2026-10-16T16:00:00Z

Content type: article

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [ai-governance](<https://devfeed.tech/topics/ai-governance.md>), [Security & Privacy](<https://devfeed.tech/topics/security-privacy.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [gpt-oss](<https://devfeed.tech/topics/gpt-oss.md>)

Tags: [ai-risk-management](<https://devfeed.tech/tags/ai-risk-management.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [open-weight-ai](<https://devfeed.tech/tags/open-weight-ai.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

Microsoft and NVIDIA introduce a shared risk taxonomy and evaluation approach for enterprises deploying open-weight models. The guidance emphasizes that risk depends on the model's use case, deployment, and safeguards, and that organizations should connect identified risks to evaluations, controls, and accountable owners.

### Source excerpt

New whitepaper from Microsoft and NVIDIA helps enterprises manage open-weight AI model risks with a shared taxonomy, evaluations, and controls. The post Managing open-weight model risk in enterprise deployments appeared first on Microsoft Security Blog.

[Next page](<https://devfeed.tech/sources/microsoft-security-blog.md?cursor=WyIyMDI2LTEwLTE2VDE2OjAwOjAwKzAwOjAwIiwgIjg3ODdiYzY1LWMwMTYtNGJlMS1iZTJhLTZmYzljODUyYmQ3OCJd>)