# You gave your AI agent access, but who is giving it orders?

DevFeed: [You gave your AI agent access, but who is giving it orders?](<https://devfeed.tech/articles/you-gave-your-ai-agent-access-but-who-is-giving-it-orders-97738.md>)

Original publisher: [Read original article](<https://www.bleepingcomputer.com/news/security/you-gave-your-ai-agent-access-but-who-is-giving-it-orders/>)

Author: Sponsored by Gen Digital

Published: 2026-10-23T14:00:10Z

Content type: article

Language: en

Sources: [BleepingComputer](<https://devfeed.tech/sources/bleepingcomputer.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [malware protection](<https://devfeed.tech/topics/malware-protection.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [credential-based attacks](<https://devfeed.tech/topics/credential-based-attacks.md>), [Access Control](<https://devfeed.tech/topics/access-control.md>), [AI Bots](<https://devfeed.tech/topics/ai-bots.md>), [malicious packages](<https://devfeed.tech/topics/malicious-packages.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-trust](<https://devfeed.tech/tags/agent-trust.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-access](<https://devfeed.tech/tags/ai-agent-access.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-guardrails](<https://devfeed.tech/tags/ai-guardrails.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [commands](<https://devfeed.tech/tags/commands.md>), [computer-help](<https://devfeed.tech/tags/computer-help.md>), [computer-security](<https://devfeed.tech/tags/computer-security.md>), [computers](<https://devfeed.tech/tags/computers.md>), [connectivity](<https://devfeed.tech/tags/connectivity.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [data](<https://devfeed.tech/tags/data.md>), [digital](<https://devfeed.tech/tags/digital.md>), [files](<https://devfeed.tech/tags/files.md>), [gen-digital](<https://devfeed.tech/tags/gen-digital.md>), [giving](<https://devfeed.tech/tags/giving.md>), [helps](<https://devfeed.tech/tags/helps.md>), [hub](<https://devfeed.tech/tags/hub.md>), [infosec](<https://devfeed.tech/tags/infosec.md>), [linux](<https://devfeed.tech/tags/linux.md>), [mac](<https://devfeed.tech/tags/mac.md>), [malicious](<https://devfeed.tech/tags/malicious.md>), [malware](<https://devfeed.tech/tags/malware.md>), [malware-removal](<https://devfeed.tech/tags/malware-removal.md>), [openclaw](<https://devfeed.tech/tags/openclaw.md>), [orders](<https://devfeed.tech/tags/orders.md>), [security](<https://devfeed.tech/tags/security.md>), [spyware](<https://devfeed.tech/tags/spyware.md>), [support](<https://devfeed.tech/tags/support.md>), [tech-support](<https://devfeed.tech/tags/tech-support.md>), [technical-support](<https://devfeed.tech/tags/technical-support.md>), [virus](<https://devfeed.tech/tags/virus.md>), [virus-removal](<https://devfeed.tech/tags/virus-removal.md>), [windows](<https://devfeed.tech/tags/windows.md>)

## AI overview

AI agents can be manipulated by malicious emails, web pages, or extensions into misusing permissions, even without a software vulnerability. Gen's proposed Agent Trust Hub layers safeguards across agent use: it scans skills and offers trusted listings; VPN for Agents provides encrypted, separate connections; and Sage intercepts shell commands, file operations, and web requests for allow, user review, or denial. Sage supports several named coding agents, but depends on integration visibility and does not replace endpoint protection. The hub also offers tools to inspect AI services' data practices. Gen describes separate AMTSO testing guidelines that distinguish detection, prevention, model refusal, and blocking legitimate activity. The excerpt presents these as complementary controls, not a single complete shield.

## Source excerpt

AI agents can be manipulated through malicious emails, websites, and plugins into executing commands, stealing data, or deleting files using their legitimate permissions. Gen Digital explains how its Agent Trust Hub helps protect agents through skill verification, secure connectivity, and runtime controls that intercept dangerous act [...]