Threat Pulse 62High
Malicious AGENTS.md in Downloads hijacks AI coding agents
Severity 6ActiveconfirmedAI and software supply chainAI-related

Forever Security found a malicious AGENTS.md on a customer machine that made a coding agent started in the Downloads folder try to install a rogue npm package. Codex followed it about 90% of the time in tests; a CLAUDE.md variant leaked a Claude Code OAuth token about half the time. Nothing for vendors to patch: the agents follow instruction files as designed.

What to do: Never start a coding agent in Downloads or your home folder; run it inside the project folder and read unfamiliar instruction files first.

AI angle: AI coding agents obey instruction files they find in the folder they start in.

· 10 days ago · one real case · bleepingcomputer.com
Sourcesbleepingcomputer.comforever.security
On X
@BleepinComputerverifiedOct 25, 15:49 UTC

AI coding agents hijacked using AGENTS.md file in Downloads folder

Open on X
Why this score

Plan rubric with caps (verified sweep, Oct 25 PM): one real case, works by design

Back to the board

Updated Nov 5, 01:45 UTC. Refreshes on its own.

Add a threat

Paste a link to an advisory, an article or an X post. A person reads every submission before it shows; nothing posts on its own.

Share

The picture people see when the link is posted
Post on XSave picture

This picture is what X, iMessage, Slack and Facebook show under the link. It is drawn fresh from the live board: the board and chart pictures update every 10 minutes, an event picture follows that event.