LiteLLM 1.107.0 poisoned on PyPI with key-stealing malware — second hijack this year
mark_k · x · 2026-10-23
LiteLLM 1.107.0 was poisoned on PyPI and Docker for about two hours. The malware runs every time Python starts, even if litellm is never imported, and steals cloud keys, SSH keys, and local Cursor and Claude configs. Attackers used stolen GitHub tokens — one belonging to an org owner — to disable branch protection and publish the release. This is the second LiteLLM hijack this year; anyone who installed it Wednesday afternoon should rotate all credentials immediately.
More from coding & agent
- We tested 12 LLM classifiers — the new classifier hype is LARP — KlausCodes · 2026-10-23
- Dev builds ESP32 desk display showing Claude Code and Codex agent status via local Go helper — tonylook · 2026-10-23
- Let your agent read its own traces: AgentsView + history tool debugging workflow — dbreunig · 2026-10-23
- YC-backed Mireye launches land search API + MCP with 160M parcels for AI agents — ycombinator · 2026-10-23
- Testing 12 decision systems: the new LARP hype around classifiers — KlausCodes · 2026-10-23
- Monid launches 'Product Hunt for agents,' ranking tools by real agent calls — claudeai · 2026-10-23