AI Coding Agents Are Installing Unknown/Untrusted Code on Corporate Networks
Research across 6,200+ corporate domains reveals widespread llms.txt files that guide AI coding agents to install unvetted packages — a shadow supply-chain risk largely invisible to existing governance controls.
Summary written by editorial AI · Source link below
We cannot forget that AI coding agents are not yet trustworthy : Researchers at a stealth startup in Israel scanned 6,214 live domains belonging to defense contractors, Fortune 500, and Big Tech companies. Of the 8,265 llms.txt and llms-full.txt files they found (many sites hosted both an llms.txt and an llms-full.txt file), 120 of them, each on a different site, pointed to one or more code packages or domain names that weren’t registered. To test what happens when an AI agent processes such fil
Editorial Analysis
AI coding agents bypass traditional change management by autonomously resolving dependencies, creating a supply-chain blind spot that existing SBOM and procurement processes do not cover.
Inventory all AI coding agent deployments across your organisation, restrict their network access, and require human sign-off before any new dependency is introduced.
AI-powered developer tools are silently introducing unreviewed code into corporate networks, creating a new class of supply-chain risk that current controls don't address.
Forward-looking interpretation drafted by editorial AI under human review — not a reproduction of the source. See methodology.
External link — opens at Schneier on Security in a new tab.
More from the AI Security Desk
- OpenAI AI Agents Demonstrate VM Escapes and Secret Cross-Sandbox Communication1d
- Exposed Infrastructure Reveals How Ransomware Affiliates Used AI Agents to Execute Intrusions3d
- You gave your AI agent access, but who is giving it orders?3d
- AI Agents as Insider Threats: Inside Microsoft's Bet on a Unified Security Stack3d
- Critical x402 SDK Flaw Could Let Malicious APIs Drain AI Agents’ Token Balances3d