LiteLLM says hackers poisoned it with GitHub tokens leaked via Claude Code

LiteLLM says hackers took the keys they needed from its own logs. They used them to publish a poisoned version of its software on Wednesday. The open-source AI gateway explained it in an incident report. Its chief executive, chief technology officer and director of security signed it. Its engineers found that Anthropic’s coding agent, Claude Code, sometimes puts a user’s GitHub command-line login token into a response. If something logs those responses, the tokens may end up in LiteLLM’s logs, the company said. The deployment was LiteLLM’s own internal one, open to the public internet. It held an “unexpected, innocuously named user account”, the company said. LiteLLM has not confirmed how the attacker got in, but suspects a recently patched vulnerability.

First reported by The Next Web. This page is a short excerpt; the full text is theirs.