# Snyk

Developer Security Platform

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

## Why the Harness Matters: Early Lessons From the Evo Code Scanning Agent Preview

DevFeed: [Why the Harness Matters: Early Lessons From the Evo Code Scanning Agent Preview](<https://devfeed.tech/articles/why-the-harness-matters-early-lessons-from-the-evo-code-scanning-agent-preview-146509.md>)

Original publisher: [Read original article](<https://snyk.io/blog/why-harness-matters-evo-code-scanning-agent/>)

Author: Brian Clark; Adrian Meier; Pauline Bolignano

Published: 2026-11-19T04:00:00Z

Content type: news

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [code security](<https://devfeed.tech/topics/code-security.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Static code analysis](<https://devfeed.tech/topics/static-code-analysis.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [Security](<https://devfeed.tech/topics/security.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-harness](<https://devfeed.tech/tags/ai-harness.md>), [ai-model](<https://devfeed.tech/tags/ai-model.md>), [ai-reasoning](<https://devfeed.tech/tags/ai-reasoning.md>), [ai-security-agents](<https://devfeed.tech/tags/ai-security-agents.md>), [blog](<https://devfeed.tech/tags/blog.md>), [budget](<https://devfeed.tech/tags/budget.md>), [claude](<https://devfeed.tech/tags/claude.md>), [code](<https://devfeed.tech/tags/code.md>), [code-scanning](<https://devfeed.tech/tags/code-scanning.md>), [code-security](<https://devfeed.tech/tags/code-security.md>), [codex](<https://devfeed.tech/tags/codex.md>), [compute](<https://devfeed.tech/tags/compute.md>), [developer](<https://devfeed.tech/tags/developer.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [harness](<https://devfeed.tech/tags/harness.md>), [interest](<https://devfeed.tech/tags/interest.md>), [precision](<https://devfeed.tech/tags/precision.md>), [preview](<https://devfeed.tech/tags/preview.md>), [security](<https://devfeed.tech/tags/security.md>), [security-labs](<https://devfeed.tech/tags/security-labs.md>), [snyk-code](<https://devfeed.tech/tags/snyk-code.md>), [tests](<https://devfeed.tech/tags/tests.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>), [vulnerability-insights](<https://devfeed.tech/tags/vulnerability-insights.md>)

### AI overview

At equal compute, Evo Code Scanning Agent's security harness found a larger share of known vulnerabilities than either same-model lab tool across 14 applications: 57% versus Claude Security's 32% on Claude Sonnet 5.5, and 66% versus Codex Security deep's 43% on GPT-6.1 Sol. Precision was lower: 65% versus 94% for Claude and 90% versus 97.5% for Codex. Each lab tool also found some vulnerabilities Evo missed. Since each pair used the same model, the article attributes differences to the surrounding harness--how it plans work, divides code, investigates candidates, and selects findings. Results are early and based on Snyk's internal benchmark of 1,426 known vulnerabilities; Evo is still in experimental preview, and no tool found them all. The authors recommend treating AI scanners as one layer alongside SAST, SCA, and code review.

### Source excerpt

In early tests, Evo Code Scanning Agent's security harness found more known vulnerabilities than Claude Security and Codex Security at the same compute budget, with lower precision. See what the results reveal about the role of the harness in AI code scanning.

## Snyk Named a Leader in The Forrester Wave™: Agentic Development Security Tools, Q4 2026

DevFeed: [Snyk Named a Leader in The Forrester Wave™: Agentic Development Security Tools, Q4 2026](<https://devfeed.tech/articles/snyk-named-a-leader-in-the-forrester-wavetm-agentic-development-security-tools-q4-2026-118948.md>)

Original publisher: [Read original article](<https://snyk.io/blog/snyk-named-leader-forrester-wave-agentic-development-security-tools-q4-2026/>)

Author: Anthony Larkin

Published: 2026-11-04T04:00:00Z

Content type: release

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [snyk](<https://devfeed.tech/topics/snyk.md>), [snyk-platform](<https://devfeed.tech/topics/snyk-platform.md>), [Application Security](<https://devfeed.tech/topics/application-security.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [code security](<https://devfeed.tech/topics/code-security.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [shadow AI](<https://devfeed.tech/topics/shadow-ai.md>), [DevSecOps](<https://devfeed.tech/topics/devsecops.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [adversarial](<https://devfeed.tech/tags/adversarial.md>), [adversarial-testing](<https://devfeed.tech/tags/adversarial-testing.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-workflows](<https://devfeed.tech/tags/agent-workflows.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-ai-adoption](<https://devfeed.tech/tags/agentic-ai-adoption.md>), [agentic-appsec](<https://devfeed.tech/tags/agentic-appsec.md>), [agentic-development](<https://devfeed.tech/tags/agentic-development.md>), [ai](<https://devfeed.tech/tags/ai.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [blog](<https://devfeed.tech/tags/blog.md>), [code-security](<https://devfeed.tech/tags/code-security.md>), [developer](<https://devfeed.tech/tags/developer.md>), [development](<https://devfeed.tech/tags/development.md>), [devops](<https://devfeed.tech/tags/devops.md>), [devsecops](<https://devfeed.tech/tags/devsecops.md>), [executive](<https://devfeed.tech/tags/executive.md>), [forrester](<https://devfeed.tech/tags/forrester.md>), [interest](<https://devfeed.tech/tags/interest.md>), [leader](<https://devfeed.tech/tags/leader.md>), [q4](<https://devfeed.tech/tags/q4.md>), [sbom](<https://devfeed.tech/tags/sbom.md>), [score](<https://devfeed.tech/tags/score.md>), [secrets](<https://devfeed.tech/tags/secrets.md>), [security](<https://devfeed.tech/tags/security.md>), [security-tools](<https://devfeed.tech/tags/security-tools.md>), [snyk](<https://devfeed.tech/tags/snyk.md>), [snyk-code](<https://devfeed.tech/tags/snyk-code.md>), [snyk-platform](<https://devfeed.tech/tags/snyk-platform.md>), [strategy](<https://devfeed.tech/tags/strategy.md>), [supply-chain-security](<https://devfeed.tech/tags/supply-chain-security.md>), [tech](<https://devfeed.tech/tags/tech.md>)

### AI overview

Snyk says it was named a Leader in Forrester's Q4 2026 Agentic Development Security Tools evaluation, with its highest score in Strategy and top scores in specified strategy and current-offering criteria. The article argues that agentic development requires governing agents' tools and actions, securing generated code and AI applications, and testing controls continuously. Snyk describes Evo by Snyk as covering those areas through Agentic AppSec for code, Agentic Development Security for agent workflows, AI-SPM for AI asset discovery and policy enforcement, and Continuous Offensive Security for ongoing adversarial validation. It presents these as parts of one platform, pairing AI reasoning with deterministic verification. The excerpt reflects Snyk's account of its evaluation and product capabilities; it does not provide the full Forrester report or comparative scores for other vendors.

### Source excerpt

Snyk is a Leader in The Forrester Wave™: Agentic Development Security Tools, Q4 2026, with the highest score in the strategy category.

## PHP2Shell Won't Be the Last. Here's Where the Next One Will Show Up First.

DevFeed: [PHP2Shell Won't Be the Last. Here's Where the Next One Will Show Up First.](<https://devfeed.tech/articles/php2shell-won-t-be-the-last-here-s-where-the-next-one-will-show-up-first-105792.md>)

Original publisher: [Read original article](<https://snyk.io/blog/php2shell-where-next-one-will-show-up-first/>)

Author: Nuno Loureiro; Ricardo Alves

Published: 2026-10-28T04:00:00Z

Content type: article

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [LLM security](<https://devfeed.tech/topics/llm-security.md>), [synthetic monitoring](<https://devfeed.tech/topics/synthetic-monitoring.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [AI software supply chain security](<https://devfeed.tech/topics/ai-software-supply-chain-security.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [ai-pentesting](<https://devfeed.tech/tags/ai-pentesting.md>), [api](<https://devfeed.tech/tags/api.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [attack](<https://devfeed.tech/tags/attack.md>), [attack-surface](<https://devfeed.tech/tags/attack-surface.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [blog](<https://devfeed.tech/tags/blog.md>), [cadence](<https://devfeed.tech/tags/cadence.md>), [clean-code](<https://devfeed.tech/tags/clean-code.md>), [code-execution](<https://devfeed.tech/tags/code-execution.md>), [container](<https://devfeed.tech/tags/container.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [cos](<https://devfeed.tech/tags/cos.md>), [devops](<https://devfeed.tech/tags/devops.md>), [devsecops](<https://devfeed.tech/tags/devsecops.md>), [docker](<https://devfeed.tech/tags/docker.md>), [enablement](<https://devfeed.tech/tags/enablement.md>), [engine](<https://devfeed.tech/tags/engine.md>), [internet](<https://devfeed.tech/tags/internet.md>), [inventory](<https://devfeed.tech/tags/inventory.md>), [php](<https://devfeed.tech/tags/php.md>), [php2shell](<https://devfeed.tech/tags/php2shell.md>), [rapid](<https://devfeed.tech/tags/rapid.md>), [repeat](<https://devfeed.tech/tags/repeat.md>), [risk](<https://devfeed.tech/tags/risk.md>), [security](<https://devfeed.tech/tags/security.md>), [snyk-container](<https://devfeed.tech/tags/snyk-container.md>), [tech](<https://devfeed.tech/tags/tech.md>), [testing](<https://devfeed.tech/tags/testing.md>), [vulnerability-insights](<https://devfeed.tech/tags/vulnerability-insights.md>)

### AI overview

PHP2Shell showed that engine-level vulnerabilities can be exploitable before application code runs, so clean code and dependency inventories may miss internet-facing risk. The article says teams need a current outside-in inventory of where PHP answers requests: package and container scans do not cover every installation route, and most PHP hosts in VirusTotal's cited data did not reveal a version string. Its response workflow is discovery, a targeted exploitability check, patching, and re-testing; repeat checks matter because disclosure details changed within days. The article distinguishes heuristic-detectable flaws such as PHP2Shell, which can be tested with payloads and observed responses, from context-dependent issues that need reasoning about intended versus actual behavior. It recommends pre-existing inventory, checks available within hours, on-demand re-tests, and testing without a known signature. It describes Snyk API & Web as providing discovery and targeted checks, with Continuous Offensive Security adding AI Pentesting and Agent Red Teaming.

### Source excerpt

PHP2Shell showed how quickly an engine-level flaw can put internet-facing applications at risk. Learn why outside-in inventory, rapid testing, and repeat checks matter before the next disclosure.

## Snyk UNFILTERED: Inside Our First-Ever Customer Summit

DevFeed: [Snyk UNFILTERED: Inside Our First-Ever Customer Summit](<https://devfeed.tech/articles/snyk-unfiltered-inside-our-first-ever-customer-summit-105793.md>)

Original publisher: [Read original article](<https://snyk.io/blog/snyk-unfiltered-customer-summit/>)

Author: Samantha Lioanag; Alysa Turner

Published: 2026-10-28T00:00:00Z

Content type: news

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [snyk](<https://devfeed.tech/topics/snyk.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [snyk-platform](<https://devfeed.tech/topics/snyk-platform.md>)

Tags: [accountability](<https://devfeed.tech/tags/accountability.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-skill](<https://devfeed.tech/tags/agent-skill.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-risk](<https://devfeed.tech/tags/ai-risk.md>), [americas](<https://devfeed.tech/tags/americas.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-agents](<https://devfeed.tech/tags/autonomous-agents.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [blog](<https://devfeed.tech/tags/blog.md>), [customer](<https://devfeed.tech/tags/customer.md>), [executive](<https://devfeed.tech/tags/executive.md>), [first](<https://devfeed.tech/tags/first.md>), [interest](<https://devfeed.tech/tags/interest.md>), [remediation](<https://devfeed.tech/tags/remediation.md>), [risk](<https://devfeed.tech/tags/risk.md>), [security](<https://devfeed.tech/tags/security.md>), [security-for-ai](<https://devfeed.tech/tags/security-for-ai.md>), [snyk](<https://devfeed.tech/tags/snyk.md>), [speed](<https://devfeed.tech/tags/speed.md>), [summit](<https://devfeed.tech/tags/summit.md>), [teams](<https://devfeed.tech/tags/teams.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>), [vulnerability-remediation](<https://devfeed.tech/tags/vulnerability-remediation.md>)

### AI overview

At Snyk's first customer summit, security leaders said AI is shifting application security challenges from detecting vulnerabilities toward assigning responsibility, governing autonomous agents, and fixing issues quickly. Their discussions highlighted the need for clear ownership and guardrails when AI generates code; closer scrutiny of AI costs, returns, and budget limits; and faster remediation through review, testing, and merge. Wider AI access spreads security responsibility across teams, while limited human review capacity is prompting interest in agents governed by controls they cannot bypass. The article presents these as unresolved questions raised by attendees, not settled solutions.

### Source excerpt

At Snyk's first customer summit, security leaders shared candid perspectives on AI risk, vulnerability remediation, and governing autonomous agents. Five themes reveal how teams are adapting security for AI speed.

## Turn Your Vulnerability Backlog Into Pull Requests With Agentic Remediation

DevFeed: [Turn Your Vulnerability Backlog Into Pull Requests With Agentic Remediation](<https://devfeed.tech/articles/turn-your-vulnerability-backlog-into-pull-requests-with-agentic-remediation-96337.md>)

Original publisher: [Read original article](<https://snyk.io/blog/evo-remediation-agent-open-preview/>)

Author: Brendan Hann; Ryan McMorrow

Published: 2026-10-22T04:00:00Z

Content type: release

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [cve remediation](<https://devfeed.tech/topics/cve-remediation.md>), [Dependency management](<https://devfeed.tech/topics/dependency-management.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-appsec](<https://devfeed.tech/tags/agentic-appsec.md>), [ai](<https://devfeed.tech/tags/ai.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [appsec](<https://devfeed.tech/tags/appsec.md>), [automated](<https://devfeed.tech/tags/automated.md>), [backlog](<https://devfeed.tech/tags/backlog.md>), [blog](<https://devfeed.tech/tags/blog.md>), [dependency](<https://devfeed.tech/tags/dependency.md>), [developer](<https://devfeed.tech/tags/developer.md>), [devops](<https://devfeed.tech/tags/devops.md>), [devsecops](<https://devfeed.tech/tags/devsecops.md>), [enablement](<https://devfeed.tech/tags/enablement.md>), [interest](<https://devfeed.tech/tags/interest.md>), [open-source-security](<https://devfeed.tech/tags/open-source-security.md>), [preview](<https://devfeed.tech/tags/preview.md>), [pull-requests](<https://devfeed.tech/tags/pull-requests.md>), [remediation](<https://devfeed.tech/tags/remediation.md>), [scm](<https://devfeed.tech/tags/scm.md>), [security](<https://devfeed.tech/tags/security.md>), [snyk-open-source](<https://devfeed.tech/tags/snyk-open-source.md>), [snyk-platform](<https://devfeed.tech/tags/snyk-platform.md>), [teams](<https://devfeed.tech/tags/teams.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>), [vulnerability-insights](<https://devfeed.tech/tags/vulnerability-insights.md>)

### AI overview

Evo Remediation Agent is in Open Preview for Snyk Open Source vulnerabilities, letting AppSec teams define recurring campaigns across selected repositories. It uses Snyk findings to plan dependency updates, applies them in a hosted sandbox, and checks builds, available tests, and rescans before opening pull requests. Developers retain review and merge control; campaigns can be restricted to fixes assessed as non-breaking. In a 307-task VulnBump benchmark, the CLI-based agent passed all four checks--dependency resolution, vulnerability removal on rescan, build success, and preservation of previously passing tests--on 90.2% of tasks, compared with 77.5% for Claude Code with Snyk findings and 59.6% for Claude Code alone; all used the same model. Campaigns require Workspaces, SCM integration, and Tenant preview access. Open Preview has a daily fix allowance, and hosted sandboxes use public package registries.

### Source excerpt

The Evo Remediation Agent is now in Open Preview, bringing automated dependency resolution to Evo Agentic AppSec. AppSec teams can now run ongoing remediation

## PHP Patches Two Critical Unauthenticated RCEs (CVE-2026-109618, CVE-2026-109619): Update Now

DevFeed: [PHP Patches Two Critical Unauthenticated RCEs (CVE-2026-109618, CVE-2026-109619): Update Now](<https://devfeed.tech/articles/php-patches-two-critical-unauthenticated-rces-cve-2026-109618-cve-2026-109619-update-now-96178.md>)

Original publisher: [Read original article](<https://snyk.io/blog/php-patches-critical-unauthenticated-rces/>)

Author: Snyk Security Research

Published: 2026-10-22T04:00:00Z

Content type: news

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [PHP](<https://devfeed.tech/topics/php.md>), [patches](<https://devfeed.tech/topics/patches.md>), [Linux](<https://devfeed.tech/topics/linux.md>), [Composer](<https://devfeed.tech/topics/composer.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [blog](<https://devfeed.tech/tags/blog.md>), [code-execution](<https://devfeed.tech/tags/code-execution.md>), [critical](<https://devfeed.tech/tags/critical.md>), [cve](<https://devfeed.tech/tags/cve.md>), [cve-2026-109618](<https://devfeed.tech/tags/cve-2026-109618.md>), [cve-2026-109619](<https://devfeed.tech/tags/cve-2026-109619.md>), [developer](<https://devfeed.tech/tags/developer.md>), [devops](<https://devfeed.tech/tags/devops.md>), [enablement](<https://devfeed.tech/tags/enablement.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [lifecycle](<https://devfeed.tech/tags/lifecycle.md>), [open-source-security](<https://devfeed.tech/tags/open-source-security.md>), [patches](<https://devfeed.tech/tags/patches.md>), [php](<https://devfeed.tech/tags/php.md>), [release](<https://devfeed.tech/tags/release.md>), [remote-code-execution](<https://devfeed.tech/tags/remote-code-execution.md>), [request](<https://devfeed.tech/tags/request.md>), [security](<https://devfeed.tech/tags/security.md>), [update](<https://devfeed.tech/tags/update.md>), [upgrade](<https://devfeed.tech/tags/upgrade.md>), [vulnerability-insights](<https://devfeed.tech/tags/vulnerability-insights.md>)

### AI overview

Two PHP request lifecycle flaws, CVE-2026-109618 and CVE-2026-109619, are rated CVSS v4.0 9.2 and can enable unauthenticated remote code execution before application code runs. One involves request cleanup after out-of-memory interruption; the other involves stale request state reused by a later request in a long-lived worker. Web-serving PHP installations are affected, including PHP-FPM, mod_php, php-cgi, FrankenPHP, and LiteSpeed; the text says mod_php is most vulnerable and describes a single-request exploit. Update to PHP 8.5.12, 8.4.27, 8.3.36, or 8.2.35, or install a patched distribution or LTS vendor package. PHP 8.1 and older need an upgrade or backport; source backports exist for 7.4, 8.0, and 8.1. Verify the version or patch level actually running on each host and image: Composer manifests do not identify the deployed interpreter. Listed temporary settings may reduce exposure to specific paths, but do not make an installation safe; the PHP security team says updating is the only safe choice.

### Source excerpt

Two critical flaws in PHP's request lifecycle can enable unauthenticated remote code execution. Upgrade to a fixed release or install a vendor backport for older versions.

## AI Model Risk Depends on What the Model Can Reach

DevFeed: [AI Model Risk Depends on What the Model Can Reach](<https://devfeed.tech/articles/ai-model-risk-depends-on-what-the-model-can-reach-92993.md>)

Original publisher: [Read original article](<https://snyk.io/blog/ai-model-risk-model-reach/>)

Author: John Carione

Published: 2026-10-21T04:00:00Z

Content type: article

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [LLM security](<https://devfeed.tech/topics/llm-security.md>), [AI software supply chain security](<https://devfeed.tech/topics/ai-software-supply-chain-security.md>), [Security](<https://devfeed.tech/topics/security.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [MSP MCP](<https://devfeed.tech/topics/msp-mcp.md>), [ML model versioning](<https://devfeed.tech/topics/ml-model-versioning.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [adversarial](<https://devfeed.tech/tags/adversarial.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-bill-of-materials](<https://devfeed.tech/tags/ai-bill-of-materials.md>), [ai-bom](<https://devfeed.tech/tags/ai-bom.md>), [ai-model](<https://devfeed.tech/tags/ai-model.md>), [ai-spm](<https://devfeed.tech/tags/ai-spm.md>), [alert](<https://devfeed.tech/tags/alert.md>), [application](<https://devfeed.tech/tags/application.md>), [aspm](<https://devfeed.tech/tags/aspm.md>), [attack](<https://devfeed.tech/tags/attack.md>), [blog](<https://devfeed.tech/tags/blog.md>), [data](<https://devfeed.tech/tags/data.md>), [executive](<https://devfeed.tech/tags/executive.md>), [interest](<https://devfeed.tech/tags/interest.md>), [risk](<https://devfeed.tech/tags/risk.md>), [sbom](<https://devfeed.tech/tags/sbom.md>), [score](<https://devfeed.tech/tags/score.md>), [security](<https://devfeed.tech/tags/security.md>), [security-labs](<https://devfeed.tech/tags/security-labs.md>), [teams](<https://devfeed.tech/tags/teams.md>), [tools](<https://devfeed.tech/tags/tools.md>), [verify](<https://devfeed.tech/tags/verify.md>)

### AI overview

A model's risk score describes tested weaknesses; application reach determines how consequential they may be. In Snyk's scan, 74.5% of 1,693 environments with detected model identifiers referenced a model scoring high on at least one attacker goal, and 49.2% referenced one scoring critical. These are investigation signals, not evidence of production use or successful attacks: only 37.5% of detected model occurrences had a matched score. Agent and MCP signals were associated with more high-scoring model references, but the study says runtime checks are needed to confirm what is active and accessible. Security teams should inventory models and unknowns, verify runtime access to data, tools and actions, switch models where tests show meaningful differences, and use access limits, output checks, approvals, monitoring and code scanning where model results cluster. The findings come from anonymized Snyk customer scans beginning September 2026.

### Source excerpt

A model's risk score is only part of the picture: its impact depends on the data, tools, and actions its application can reach. Learn how security teams can verify that reach and choose targeted controls.

## AI Is Calling In Every Risk You've Accepted: Seven Insights From The AI Security Panel: Unfiltered

DevFeed: [AI Is Calling In Every Risk You've Accepted: Seven Insights From The AI Security Panel: Unfiltered](<https://devfeed.tech/articles/ai-is-calling-in-every-risk-you-ve-accepted-seven-insights-from-the-ai-security-panel-unfiltered-92994.md>)

Original publisher: [Read original article](<https://snyk.io/blog/ai-security-panel-unfiltered/>)

Author: Snyk Team

Published: 2026-10-21T00:00:00Z

Content type: article

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [ai security](<https://devfeed.tech/topics/ai-security.md>), [Cybersecurity](<https://devfeed.tech/topics/cybersecurity.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [code security](<https://devfeed.tech/topics/code-security.md>), [alert triage](<https://devfeed.tech/topics/alert-triage.md>), [principle of ephemerality](<https://devfeed.tech/topics/principle-of-ephemerality.md>)

Tags: [accountability](<https://devfeed.tech/tags/accountability.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-harnesses](<https://devfeed.tech/tags/agent-harnesses.md>), [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-ai-adoption](<https://devfeed.tech/tags/agentic-ai-adoption.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-adoption](<https://devfeed.tech/tags/ai-adoption.md>), [ai-security](<https://devfeed.tech/tags/ai-security.md>), [americas](<https://devfeed.tech/tags/americas.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [blog](<https://devfeed.tech/tags/blog.md>), [defense](<https://devfeed.tech/tags/defense.md>), [developer](<https://devfeed.tech/tags/developer.md>), [executive](<https://devfeed.tech/tags/executive.md>), [insights](<https://devfeed.tech/tags/insights.md>), [open-source-security](<https://devfeed.tech/tags/open-source-security.md>), [panel](<https://devfeed.tech/tags/panel.md>), [remediation](<https://devfeed.tech/tags/remediation.md>), [risk](<https://devfeed.tech/tags/risk.md>), [risks](<https://devfeed.tech/tags/risks.md>), [security](<https://devfeed.tech/tags/security.md>), [snyk-open-source](<https://devfeed.tech/tags/snyk-open-source.md>), [speed](<https://devfeed.tech/tags/speed.md>), [vulnerability-insights](<https://devfeed.tech/tags/vulnerability-insights.md>)

### AI overview

The panel's shared diagnosis is that AI makes attacks cheaper and faster, while the growing bottleneck is fixing vulnerabilities before attackers can chain them. Leaders described agents as a new attack surface because they act on their own and may accumulate access; they recommended giving each agent a distinct identity, job-scoped access that expires, and an audit trail. They argued for machine-speed defense: automate safe remediation and SOC actions, with people handling exceptions and judgment. The panel differed on how to supervise nondeterministic systems and who should set AI accountability rules. Suggested near-term steps include scanning organizational code and infrastructure with frontier models, auditing agent access, enabling strong multi-factor authentication, and improving the ratio of issues fixed to issues found. The article cites Snyk research finding flaws in 36.82% of 3,984 scanned agent skills, and reports that only about 10% of recorded vulnerability findings with known fixes were resolved.

### Source excerpt

AI is making attacks cheaper and faster, exposing risks organizations already carry. Four security leaders share why machine-speed defense and faster remediation are now essential.

## Introducing Evo Agentic AppSec: Security That Keeps Up With AI Development

DevFeed: [Introducing Evo Agentic AppSec: Security That Keeps Up With AI Development](<https://devfeed.tech/articles/introducing-evo-agentic-appsec-security-that-keeps-up-with-ai-development-87984.md>)

Original publisher: [Read original article](<https://snyk.io/blog/announcing-snyk-agentic-appsec/>)

Author: Brendan Hann; Sergey Gerasimenko

Published: 2026-10-15T04:00:00Z

Content type: release

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [Application Security](<https://devfeed.tech/topics/application-security.md>), [Agentic SOC](<https://devfeed.tech/topics/agentic-soc.md>), [snyk-security-intel](<https://devfeed.tech/topics/snyk-security-intel.md>), [code security](<https://devfeed.tech/topics/code-security.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>)

Tags: [agentic-appsec](<https://devfeed.tech/tags/agentic-appsec.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-development](<https://devfeed.tech/tags/ai-development.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [aspm](<https://devfeed.tech/tags/aspm.md>), [blog](<https://devfeed.tech/tags/blog.md>), [ci-cd](<https://devfeed.tech/tags/ci-cd.md>), [code-security](<https://devfeed.tech/tags/code-security.md>), [developer](<https://devfeed.tech/tags/developer.md>), [devops](<https://devfeed.tech/tags/devops.md>), [devsecops](<https://devfeed.tech/tags/devsecops.md>), [executive](<https://devfeed.tech/tags/executive.md>), [interest](<https://devfeed.tech/tags/interest.md>), [open-source-security](<https://devfeed.tech/tags/open-source-security.md>), [secrets](<https://devfeed.tech/tags/secrets.md>), [security](<https://devfeed.tech/tags/security.md>), [snyk-code](<https://devfeed.tech/tags/snyk-code.md>), [snyk-open-source](<https://devfeed.tech/tags/snyk-open-source.md>), [snyk-platform](<https://devfeed.tech/tags/snyk-platform.md>), [supply-chain-security](<https://devfeed.tech/tags/supply-chain-security.md>)

### AI overview

Snyk introduces Evo Agentic AppSec, a team of security agents intended to manage application security throughout development and for shipped applications. The agents assess threats, detect vulnerabilities, block malicious packages, propose fixes, and verify results, while teams set policies and retain approval authority. The announcement describes the product as an upcoming addition to Evo.

### Source excerpt

AI-driven development is outpacing traditional security workflows. Snyk's Agentic AppSec uses security agents to find, fix, and verify vulnerabilities continuously, while humans set the bar.

## VulnBump: Can AI Agents Fix Vulnerable Dependencies Without Breaking the Build?

DevFeed: [VulnBump: Can AI Agents Fix Vulnerable Dependencies Without Breaking the Build?](<https://devfeed.tech/articles/vulnbump-can-ai-agents-fix-vulnerable-dependencies-without-breaking-the-build-87985.md>)

Original publisher: [Read original article](<https://snyk.io/blog/vulnbump/>)

Author: Ryan McMorrow; Gabija Pasiunaite

Published: 2026-10-15T04:00:00Z

Content type: article

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [software composition analysis](<https://devfeed.tech/topics/software-composition-analysis.md>), [code security](<https://devfeed.tech/topics/code-security.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [appsec](<https://devfeed.tech/tags/appsec.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [blog](<https://devfeed.tech/tags/blog.md>), [dependencies](<https://devfeed.tech/tags/dependencies.md>), [developer](<https://devfeed.tech/tags/developer.md>), [interest](<https://devfeed.tech/tags/interest.md>), [security](<https://devfeed.tech/tags/security.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>)

### AI overview

Snyk's VulnBump benchmark evaluates AI agents on 307 real upgrades of vulnerable dependencies, requiring each fix to remove vulnerabilities while preserving installation, build, and test success. Evo Remediation Agent passed 90.2% of upgrades, compared with 77.5% for Claude Code given Snyk's scan and recommendation and 59.6% for Claude Code unaided. The article finds that security data and a verification loop combining rescans, builds, and tests materially affect results, while major framework migrations remain difficult for all tested agents.

### Source excerpt

VulnBump tests AI agents on 307 real dependency upgrades. A fix counts only if the vulnerability is gone and the build and tests stay green.

## Live attack testing confirmed exploit chains that code analysis alone did not

DevFeed: [Live attack testing confirmed exploit chains that code analysis alone did not](<https://devfeed.tech/articles/frontier-models-found-the-vulnerabilities-only-the-attacker-found-the-chains-66819.md>)

Original publisher: [Read original article](<https://snyk.io/blog/frontier-models-vulnerabilities-attacker-chains/>)

Author: Nuno Loureiro; Brian Clark

Published: 2026-10-07T04:00:00Z

Content type: comparison

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [Security](<https://devfeed.tech/topics/security.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [exploit chaining](<https://devfeed.tech/topics/exploit-chaining.md>), [Static code analysis](<https://devfeed.tech/topics/static-code-analysis.md>), [code security](<https://devfeed.tech/topics/code-security.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [blog](<https://devfeed.tech/tags/blog.md>), [but](<https://devfeed.tech/tags/but.md>), [claude-code-security](<https://devfeed.tech/tags/claude-code-security.md>), [code-security](<https://devfeed.tech/tags/code-security.md>), [exploit](<https://devfeed.tech/tags/exploit.md>), [exploitability](<https://devfeed.tech/tags/exploitability.md>), [false-positives](<https://devfeed.tech/tags/false-positives.md>), [frontier-models](<https://devfeed.tech/tags/frontier-models.md>), [interest](<https://devfeed.tech/tags/interest.md>), [security](<https://devfeed.tech/tags/security.md>), [vulnerability-insights](<https://devfeed.tech/tags/vulnerability-insights.md>)

### AI overview

The article compares Evo Continuous Offensive Security (COS), which tests a live application, with Claude Security using Mythos, which analyzes source code. In a single run against the deliberately vulnerable TaintedPort app, Evo COS confirmed 10 of 15 known exploit chains and demonstrated an SSRF-to-administrator-token takeover path. Claude Security found one more critical vulnerability, while Evo COS detected more vulnerabilities overall and reported higher precision with fewer false positives. The article argues that dynamic and static testing complement each other.

### Source excerpt

Static analysis found the flaws, but only live attack testing proved how they could be chained into breaches. A comparison of Evo COS, Claude Security, and Claude Code Security.

## Autonomous Attacks Are Already Here. The Defense Has to Match Their Speed.

DevFeed: [Autonomous Attacks Are Already Here. The Defense Has to Match Their Speed.](<https://devfeed.tech/articles/autonomous-attacks-are-already-here-the-defense-has-to-match-their-speed-66818.md>)

Original publisher: [Read original article](<https://snyk.io/blog/autonomous-attacks-already-here-defense-match-their-speed/>)

Author: Snyk Team

Published: 2026-10-07T00:00:00Z

Content type: article

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [LLM security](<https://devfeed.tech/topics/llm-security.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [frontend security](<https://devfeed.tech/topics/frontend-security.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [blog](<https://devfeed.tech/tags/blog.md>), [code-security](<https://devfeed.tech/tags/code-security.md>), [developer](<https://devfeed.tech/tags/developer.md>), [devops](<https://devfeed.tech/tags/devops.md>), [devsecops](<https://devfeed.tech/tags/devsecops.md>), [executive](<https://devfeed.tech/tags/executive.md>), [interest](<https://devfeed.tech/tags/interest.md>), [sbom](<https://devfeed.tech/tags/sbom.md>), [secrets](<https://devfeed.tech/tags/secrets.md>), [security](<https://devfeed.tech/tags/security.md>), [snyk-apprisk](<https://devfeed.tech/tags/snyk-apprisk.md>), [snyk-code](<https://devfeed.tech/tags/snyk-code.md>), [snyk-open-source](<https://devfeed.tech/tags/snyk-open-source.md>), [snyk-platform](<https://devfeed.tech/tags/snyk-platform.md>), [supply-chain-security](<https://devfeed.tech/tags/supply-chain-security.md>), [vulnerability-insights](<https://devfeed.tech/tags/vulnerability-insights.md>)

### AI overview

The article argues that autonomous attacks have shortened the time available to security teams and describes a four-part response: discover, remediate, validate, and prevent. It highlights using autonomous testing on high-impact applications, applying security context as AI agents write code, tracking new findings against resolved findings, and measuring how often proposed fixes merge without human rewrites.

### Source excerpt

Autonomous attackers are shrinking the window for defense. Learn how continuous discovery, remediation, validation, and prevention can help security teams keep pace.

## Why AI Coding Agents Keep Writing Broken Access Control

DevFeed: [Why AI Coding Agents Keep Writing Broken Access Control](<https://devfeed.tech/articles/why-ai-coding-agents-keep-writing-broken-access-control-63387.md>)

Original publisher: [Read original article](<https://snyk.io/blog/ai-coding-agents-broken-access-control/>)

Author: Brendan Hann

Published: 2026-10-01T04:00:00Z

Content type: article

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [Access Control](<https://devfeed.tech/topics/access-control.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [devrig](<https://devfeed.tech/topics/devrig.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [api-security](<https://devfeed.tech/tags/api-security.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [aspm](<https://devfeed.tech/tags/aspm.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [blog](<https://devfeed.tech/tags/blog.md>), [broken-access-control](<https://devfeed.tech/tags/broken-access-control.md>), [code-security](<https://devfeed.tech/tags/code-security.md>), [developer](<https://devfeed.tech/tags/developer.md>), [interest](<https://devfeed.tech/tags/interest.md>), [security](<https://devfeed.tech/tags/security.md>), [snyk-platform](<https://devfeed.tech/tags/snyk-platform.md>)

### AI overview

The article explains why AI coding agents can produce authorization logic that looks correct but fails to enforce product-specific ownership rules, exposing one tenant's data to another. It describes the limits of static analysis for object-level authorization and recommends documenting ownership rules, reviewing agent-authored changes for authorization, adding cross-tenant tests, and using deeper contextual analysis.

### Source excerpt

AI coding agents can produce authorization logic that compiles and passes review while exposing one tenant's data to another. Learn why broken access control is difficult to detect and how to prevent it.

## Evo ADS Govern Agent Behavior Goes GA: Bringing MCP Usage Under Control

DevFeed: [Evo ADS Govern Agent Behavior Goes GA: Bringing MCP Usage Under Control](<https://devfeed.tech/articles/evo-ads-govern-agent-behavior-goes-ga-bringing-mcp-usage-under-control-62670.md>)

Original publisher: [Read original article](<https://snyk.io/blog/evo-ads-govern-agent-behavior-ga/>)

Author: Daniel Berman

Published: 2026-09-30T04:00:00Z

Content type: news

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [ecosystem-security](<https://devfeed.tech/topics/ecosystem-security.md>), [cursor](<https://devfeed.tech/topics/cursor.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [Postman Agent Mode](<https://devfeed.tech/topics/postman-agent-mode.md>), [ReAct agent Python](<https://devfeed.tech/topics/react-agent-python.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [blog](<https://devfeed.tech/tags/blog.md>), [codex](<https://devfeed.tech/tags/codex.md>), [developer](<https://devfeed.tech/tags/developer.md>), [devops](<https://devfeed.tech/tags/devops.md>), [devsecops](<https://devfeed.tech/tags/devsecops.md>), [governance](<https://devfeed.tech/tags/governance.md>), [interest](<https://devfeed.tech/tags/interest.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [security](<https://devfeed.tech/tags/security.md>), [snyk-platform](<https://devfeed.tech/tags/snyk-platform.md>), [supply-chain-security](<https://devfeed.tech/tags/supply-chain-security.md>)

### AI overview

Evo ADS Govern Agent Behavior is generally available, beginning with MCP Governance. The capability lets security and platform teams discover MCP servers, define which are allowed, and log or block their use across Claude Code, Cursor, Codex, and GitHub Copilot. MCP connects AI coding agents to external tools and data, but does not itself determine which connections should be trusted or permitted.

### Source excerpt

Evo ADS Govern Agent Behavior is now generally available, starting with MCP Governance. Discover, approve, monitor, log, and block MCP server usage across leading AI coding agents.

## What Is Agentic AppSec?

DevFeed: [What Is Agentic AppSec?](<https://devfeed.tech/articles/what-is-agentic-appsec-62671.md>)

Original publisher: [Read original article](<https://snyk.io/blog/what-is-agentic-appsec/>)

Author: Brendan Hann

Published: 2026-09-30T04:00:00Z

Content type: article

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [Application Security](<https://devfeed.tech/topics/application-security.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-appsec](<https://devfeed.tech/tags/agentic-appsec.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [blog](<https://devfeed.tech/tags/blog.md>), [developer](<https://devfeed.tech/tags/developer.md>), [devops](<https://devfeed.tech/tags/devops.md>), [devsecops](<https://devfeed.tech/tags/devsecops.md>), [security](<https://devfeed.tech/tags/security.md>), [snyk-platform](<https://devfeed.tech/tags/snyk-platform.md>)

### AI overview

Agentic AppSec uses a team of AI security agents to run an organization's application security program, from understanding applications and modeling threats to finding, prioritizing, and fixing vulnerabilities. The article presents this approach as a response to code and vulnerability backlogs that outpace human-led security processes.

### Source excerpt

Learn how Agentic AppSec uses grounded, bounded, and independently verified AI agents to run the application security loop.

## Your Vulnerability Backlog Is No Longer Technical Debt, It's an Attack Surface

DevFeed: [Your Vulnerability Backlog Is No Longer Technical Debt, It's an Attack Surface](<https://devfeed.tech/articles/your-vulnerability-backlog-is-no-longer-technical-debt-it-s-an-attack-surface-59087.md>)

Original publisher: [Read original article](<https://snyk.io/blog/vulnerability-backlog-attack-surface/>)

Author: Brendan Hann

Published: 2026-09-24T04:00:00Z

Content type: opinion

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>), [Security](<https://devfeed.tech/topics/security.md>), [Risk](<https://devfeed.tech/topics/risk.md>), [Exploit](<https://devfeed.tech/topics/exploit.md>), [Code](<https://devfeed.tech/topics/code.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [attack-surface](<https://devfeed.tech/tags/attack-surface.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [blog](<https://devfeed.tech/tags/blog.md>), [developer](<https://devfeed.tech/tags/developer.md>), [development](<https://devfeed.tech/tags/development.md>), [devops](<https://devfeed.tech/tags/devops.md>), [risk](<https://devfeed.tech/tags/risk.md>), [security](<https://devfeed.tech/tags/security.md>), [technical](<https://devfeed.tech/tags/technical.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>), [vulnerability-insights](<https://devfeed.tech/tags/vulnerability-insights.md>)

### AI overview

The article argues that vulnerability backlogs should no longer be treated as manageable technical debt because changing exploitation risks, faster code production, and agentic development are increasing the attack surface. It calls for security programs to reconsider triage thresholds, staffing assumptions, and remediation workflows.

### Source excerpt

A growing vulnerability backlog is more than technical debt: it is an attack surface. Learn why outdated risk assumptions, automated attackers, and chained findings demand a new approach.

## Evo Announces an MCP Server for Querying AI Assets, Risks, and Policies

DevFeed: [Evo Announces an MCP Server for Querying AI Assets, Risks, and Policies](<https://devfeed.tech/articles/so-i-asked-my-agent-instead-58061.md>)

Original publisher: [Read original article](<https://snyk.io/blog/so-i-asked-my-agent-instead/>)

Author: Nina Kanti; John Carione

Published: 2026-09-22T04:00:00Z

Content type: release

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [dashboards](<https://devfeed.tech/topics/dashboards.md>), [data](<https://devfeed.tech/topics/data.md>), [Repository](<https://devfeed.tech/topics/repository.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [cursor](<https://devfeed.tech/topics/cursor.md>)

Tags: [agent-harness](<https://devfeed.tech/tags/agent-harness.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-security](<https://devfeed.tech/tags/ai-security.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [blog](<https://devfeed.tech/tags/blog.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [code](<https://devfeed.tech/tags/code.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [dashboard](<https://devfeed.tech/tags/dashboard.md>), [data](<https://devfeed.tech/tags/data.md>), [developer](<https://devfeed.tech/tags/developer.md>), [devops](<https://devfeed.tech/tags/devops.md>), [devsecops](<https://devfeed.tech/tags/devsecops.md>), [enablement](<https://devfeed.tech/tags/enablement.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-servers](<https://devfeed.tech/tags/mcp-servers.md>), [models](<https://devfeed.tech/tags/models.md>), [remote](<https://devfeed.tech/tags/remote.md>), [repository](<https://devfeed.tech/tags/repository.md>), [security](<https://devfeed.tech/tags/security.md>), [snyk-platform](<https://devfeed.tech/tags/snyk-platform.md>)

### AI overview

Evo announces a remote MCP server that lets teams query AI assets, associated risks, policies, and violations from tools such as Cursor and Claude Code. It can inventory models, agents, MCP servers, skills, repositories, and developer machines, then generate dashboards from query results.

### Source excerpt

Ask your Evo tenant about models, MCP servers, and skills across your AI estate, from the client you already work in.

## The AI Hurricane Is Here

DevFeed: [The AI Hurricane Is Here](<https://devfeed.tech/articles/the-ai-hurricane-is-here-26629.md>)

Original publisher: [Read original article](<https://snyk.io/blog/ai-hurricane-is-here/>)

Author: Manoj Nair

Published: 2026-09-15T04:00:00Z

Content type: opinion

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>), [Security](<https://devfeed.tech/topics/security.md>), [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [audit trail](<https://devfeed.tech/topics/audit-trail.md>)

Tags: [agentic-development](<https://devfeed.tech/tags/agentic-development.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [audit-trail](<https://devfeed.tech/tags/audit-trail.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [blog](<https://devfeed.tech/tags/blog.md>), [code-security](<https://devfeed.tech/tags/code-security.md>), [developer](<https://devfeed.tech/tags/developer.md>), [executive](<https://devfeed.tech/tags/executive.md>), [security](<https://devfeed.tech/tags/security.md>), [security-labs](<https://devfeed.tech/tags/security-labs.md>), [snyk-platform](<https://devfeed.tech/tags/snyk-platform.md>), [snyk-security-intel](<https://devfeed.tech/tags/snyk-security-intel.md>), [supply-chain-security](<https://devfeed.tech/tags/supply-chain-security.md>), [tech](<https://devfeed.tech/tags/tech.md>), [validation](<https://devfeed.tech/tags/validation.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>), [vulnerability-insights](<https://devfeed.tech/tags/vulnerability-insights.md>)

### AI overview

The article argues that AI is accelerating software creation and cyberattacks, widening the gap between machine-speed development and slower validation. It calls for securing agentic development, enforcing runtime controls, maintaining inventories and audit trails for production AI applications, and using independent validation.

### Source excerpt

AI is accelerating software creation and cyberattacks alike. Leaders must secure agents and code at inception, enforce controls at runtime, and validate defenses independently.

## Is prevention essentially a solved problem?

DevFeed: [Is prevention essentially a solved problem?](<https://devfeed.tech/articles/is-prevention-essentially-a-solved-problem-7988.md>)

Original publisher: [Read original article](<https://snyk.io/blog/is-prevention-solved/>)

Author: Ezra Tanzer

Published: 2026-09-10T04:00:00Z

Content type: opinion

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [AI Development](<https://devfeed.tech/topics/ai-development.md>), [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [Code](<https://devfeed.tech/topics/code.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [blog](<https://devfeed.tech/tags/blog.md>), [code](<https://devfeed.tech/tags/code.md>), [code-security](<https://devfeed.tech/tags/code-security.md>), [cost](<https://devfeed.tech/tags/cost.md>), [developer](<https://devfeed.tech/tags/developer.md>), [devops](<https://devfeed.tech/tags/devops.md>), [devsecops](<https://devfeed.tech/tags/devsecops.md>), [secrets](<https://devfeed.tech/tags/secrets.md>), [security](<https://devfeed.tech/tags/security.md>), [snyk-code](<https://devfeed.tech/tags/snyk-code.md>), [snyk-open-source](<https://devfeed.tech/tags/snyk-open-source.md>), [snyk-platform](<https://devfeed.tech/tags/snyk-platform.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>), [vulnerability-insights](<https://devfeed.tech/tags/vulnerability-insights.md>)

### AI overview

The article argues that preventing vulnerabilities in agent-generated code is architecturally understood, but organizations must apply the appropriate controls throughout a changing development lifecycle. It says prompts can influence code but cannot reliably constrain agents, and that earlier security intervention reduces model-token cost, human attention, and the risk of an incorrect fix.

### Source excerpt

Prevention in agent-generated code is architecturally solved--but choosing controls that protect security without slowing development remains the challenge.

## Why Your AI Application Is Exposed

DevFeed: [Why Your AI Application Is Exposed](<https://devfeed.tech/articles/why-your-ai-application-is-exposed-8254.md>)

Original publisher: [Read original article](<https://snyk.io/blog/why-your-ai-application-is-exposed/>)

Author: Damian Tommasino

Published: 2026-08-26T04:00:00Z

Content type: article

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [Application Security](<https://devfeed.tech/topics/application-security.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Security Attacks](<https://devfeed.tech/topics/security-attacks.md>), [data](<https://devfeed.tech/topics/data.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-red-team](<https://devfeed.tech/tags/ai-red-team.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [blog](<https://devfeed.tech/tags/blog.md>), [devops](<https://devfeed.tech/tags/devops.md>), [executive](<https://devfeed.tech/tags/executive.md>), [interest](<https://devfeed.tech/tags/interest.md>), [llm](<https://devfeed.tech/tags/llm.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [rag](<https://devfeed.tech/tags/rag.md>), [security](<https://devfeed.tech/tags/security.md>), [testing](<https://devfeed.tech/tags/testing.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>)

### AI overview

The article explains why AI applications can pass conventional security scans and model evaluations while remaining exploitable through chained interactions among prompts, language models, retrieval, tools, and backend workflows. It presents DAST, AI penetration testing, and AI red teaming as complementary lenses for identifying exposed surfaces, exploitable paths, and real-world adversary outcomes.

### Source excerpt

AI applications can pass security scans yet remain exploitable through chained attacks across models, tools, data, and business workflows. Learn how DAST, AI pentesting, and red teaming work together to expose end-to-end risk.

## Remediation Agents, Demystified: Why Fixing Beats Finding

DevFeed: [Remediation Agents, Demystified: Why Fixing Beats Finding](<https://devfeed.tech/articles/remediation-agents-demystified-why-fixing-beats-finding-8066.md>)

Original publisher: [Read original article](<https://snyk.io/blog/remediation-agents-demystified/>)

Author: Snyk Team

Published: 2026-08-19T00:00:00Z

Content type: article

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [Application Security](<https://devfeed.tech/topics/application-security.md>), [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [Responsibility & Safety](<https://devfeed.tech/topics/responsibility-safety.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [aspm](<https://devfeed.tech/tags/aspm.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [ci-cd](<https://devfeed.tech/tags/ci-cd.md>), [code-security](<https://devfeed.tech/tags/code-security.md>), [community](<https://devfeed.tech/tags/community.md>), [developer](<https://devfeed.tech/tags/developer.md>), [devops](<https://devfeed.tech/tags/devops.md>), [devsecops](<https://devfeed.tech/tags/devsecops.md>), [enablement](<https://devfeed.tech/tags/enablement.md>), [interest](<https://devfeed.tech/tags/interest.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [live-stream](<https://devfeed.tech/tags/live-stream.md>), [node-js](<https://devfeed.tech/tags/node-js.md>), [pull-requests](<https://devfeed.tech/tags/pull-requests.md>), [security](<https://devfeed.tech/tags/security.md>), [snyk-code](<https://devfeed.tech/tags/snyk-code.md>), [snyk-open-source](<https://devfeed.tech/tags/snyk-open-source.md>), [snyk-platform](<https://devfeed.tech/tags/snyk-platform.md>), [validation](<https://devfeed.tech/tags/validation.md>), [vs-code](<https://devfeed.tech/tags/vs-code.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>)

### AI overview

Snyk's Remediation Agent is presented as a public-preview solution for the growing security-issue backlog. The article explains how coding agents can increase vulnerabilities, why deterministic remediation advice has not been enough, and how validation helps turn fixes into mergeable pull requests.

### Source excerpt

See how Snyk's Remediation Agent uses security intelligence, breakability analysis, and validation to turn vulnerabilities into mergeable pull requests.

## Benchmarking Secure-and-Functional Remediation and How Snyk Agent Fix Lifts Frontier-Model Fix Rates by over 14%

DevFeed: [Benchmarking Secure-and-Functional Remediation and How Snyk Agent Fix Lifts Frontier-Model Fix Rates by over 14%](<https://devfeed.tech/articles/benchmarking-secure-and-functional-remediation-and-how-snyk-agent-fix-lifts-frontier-model-fix-rates-by-over-14-8109.md>)

Original publisher: [Read original article](<https://snyk.io/blog/snyk-agent-fix-remediation-benchmark/>)

Author: Stephen Thoemmes

Published: 2026-08-18T04:00:00Z

Content type: article

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [JavaScript](<https://devfeed.tech/topics/javascript.md>), [Python](<https://devfeed.tech/topics/python.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [blog](<https://devfeed.tech/tags/blog.md>), [code-security](<https://devfeed.tech/tags/code-security.md>), [developer](<https://devfeed.tech/tags/developer.md>), [devops](<https://devfeed.tech/tags/devops.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [interest](<https://devfeed.tech/tags/interest.md>), [java](<https://devfeed.tech/tags/java.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [performance](<https://devfeed.tech/tags/performance.md>), [python](<https://devfeed.tech/tags/python.md>), [security](<https://devfeed.tech/tags/security.md>), [security-labs](<https://devfeed.tech/tags/security-labs.md>), [snyk-code](<https://devfeed.tech/tags/snyk-code.md>), [snyk-security-intel](<https://devfeed.tech/tags/snyk-security-intel.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>), [vulnerability-insights](<https://devfeed.tech/tags/vulnerability-insights.md>)

### AI overview

A benchmark of about 150 vulnerable JavaScript, Java, and Python samples evaluates whether frontier models produce fixes that are both secure and functional. The article reports that models working alone reach roughly 72-75%, while Snyk Intelligence raises Opus 4.6 from 74.6% to 85.4% and improves Python results from 64% to 88%.

### Source excerpt

A benchmark of secure, functional vulnerability fixes across JavaScript, Java, and Python shows Snyk Intelligence helps frontier models break past a 72-75% performance plateau.

## Show, Don't Tell: What Evo Continuous Offensive Security Found in a Real Enterprise SaaS

DevFeed: [Show, Don't Tell: What Evo Continuous Offensive Security Found in a Real Enterprise SaaS](<https://devfeed.tech/articles/show-don-t-tell-what-evo-continuous-offensive-security-found-in-a-real-enterprise-saas-8243.md>)

Original publisher: [Read original article](<https://snyk.io/blog/what-evo-cos-found-real-enterprise-saas/>)

Author: Nuno Loureiro; Luis Grangeia

Published: 2026-08-10T00:00:00Z

Content type: article

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [Security](<https://devfeed.tech/topics/security.md>), [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>), [Authorization](<https://devfeed.tech/topics/authorization.md>), [Software as a service](<https://devfeed.tech/topics/saas.md>), [Microservices](<https://devfeed.tech/topics/microservices.md>), [Front end](<https://devfeed.tech/topics/frontend.md>), [API](<https://devfeed.tech/topics/api.md>), [App](<https://devfeed.tech/topics/app.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Trustworthy AI](<https://devfeed.tech/topics/trustworthy-ai.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [api](<https://devfeed.tech/tags/api.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [applications](<https://devfeed.tech/tags/applications.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [blog](<https://devfeed.tech/tags/blog.md>), [customer](<https://devfeed.tech/tags/customer.md>), [customer-featured](<https://devfeed.tech/tags/customer-featured.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [devops](<https://devfeed.tech/tags/devops.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [frontend](<https://devfeed.tech/tags/frontend.md>), [interest](<https://devfeed.tech/tags/interest.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [saas](<https://devfeed.tech/tags/saas.md>), [security](<https://devfeed.tech/tags/security.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>), [vulnerability-insights](<https://devfeed.tech/tags/vulnerability-insights.md>), [web](<https://devfeed.tech/tags/web.md>)

### AI overview

Evo Continuous Offensive Security (COS) is presented as an autonomous offensive-security system combining AI pentesting, agent red teaming, and dynamic testing. The article reports a real assessment of a multi-tenant enterprise SaaS application that uncovered 33 confirmed vulnerabilities, including tenant-wide compromise and critical authorization flaws.

### Source excerpt

A real Evo Continuous Offensive Security assessment uncovered 33 confirmed vulnerabilities in a multi-tenant enterprise SaaS, including tenant-wide compromise and critical authorization flaws.

## Continuous Offensive Security & AI Pentesting: 20 FAQs

DevFeed: [Continuous Offensive Security & AI Pentesting: 20 FAQs](<https://devfeed.tech/articles/continuous-offensive-security-ai-pentesting-20-faqs-7871.md>)

Original publisher: [Read original article](<https://snyk.io/blog/continuous-offensive-security-ai-pentesting-20-faqs/>)

Author: Snyk Team

Published: 2026-08-05T04:00:00Z

Content type: article

Language: en

Sources: [Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [Application Security](<https://devfeed.tech/topics/application-security.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [apis](<https://devfeed.tech/tags/apis.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [blog](<https://devfeed.tech/tags/blog.md>), [cos](<https://devfeed.tech/tags/cos.md>), [event-driven](<https://devfeed.tech/tags/event-driven.md>), [security](<https://devfeed.tech/tags/security.md>), [snyk-platform](<https://devfeed.tech/tags/snyk-platform.md>), [testing](<https://devfeed.tech/tags/testing.md>), [validation](<https://devfeed.tech/tags/validation.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>)

### AI overview

An FAQ-style article on continuous offensive security, combining recurring and event-driven testing with DAST, AI penetration testing, and AI red teaming to identify and validate application risk as applications change.

### Source excerpt

Get answers to 20 common questions about continuous offensive security, AI penetration testing, DAST, and AI red teaming.

[Next page](<https://devfeed.tech/sources/blog-rss-feed-snyk.md?cursor=WyIyMDI2LTA4LTA1VDA0OjAwOjAwKzAwOjAwIiwgIjQ5OWI4YTgwLTc2OTktNDg1Ni1hNDc5LTA1OTI0YjEzZjQ0ZCJd>)