Article 77FBS An LLM agent attempts to compromise a project on GitHub

An LLM agent attempts to compromise a project on GitHub

by
corbet
from LWN.net on (#77FBS)
The AI Security Institute has released adetailed report on an security incident of its own making. TheInstitute set some LLM agents loose on the Internet with a securitychallenge; soon they were creating malware-laden pull requests andsock-puppet accounts to promote them.

The agent opened a malicious pull request (PR) to REPO_A andpursued a number of strategies to get it merged:
  1. Repeatedly commented on the PR with sockpuppet accounts to manufacture consensus and pressure the maintainer into approving with minimal review.
  2. Opened a GitHub Issue in another repository (also owned by PERSON_A) containing a prompt injection for other coding agents. The malicious instructions were addressed to issue-triage AI coding agents and invisible to humans viewing the website.
  3. Sent multiple emails to PERSON_A and PERSON_B, with different pretexts to get them to run malicious code. Over the course of the sample, the agent sent five emails, some containing malware, others aimed at persuading a maintainer to accept the pull request.

It would be surprising if this were the only incident of this type; theonly real difference here is that the people involved are documenting whathappened.

External Content
Source RSS or Atom Feed
Feed Location http://lwn.net/headlines/rss
Feed Title LWN.net
Feed Link https://lwn.net/
Reply 0 comments