Leaked LiteLLM Master Key Led to Malicious PyPI Release and Credential Theft
Review INC-RW-0013
A human attacker used AI as a tool.
Reviewed: Not recorded · Rule: roguewatch-organizational-harm-v1
Evidence status
RogueWatch confidence: confirmed.
Dates and discovery
- Incident date
- 2026-10-21
- Added to research / record
- Posted to RogueWatch
- No linked public incident
- First observed
- Not recorded
- Discovery channel
- Not recorded
Related incident records: RW-0013
Dates use America/Los_Angeles. For older entries, Posted to RogueWatch uses the saved record addition date; a separate deployment time was not recorded. Future posting timestamps record first public qualification. Source publication and incident occurrence are separate.
Sources
- Leaked LiteLLM Master Key Let Attackers Steal GitHub Tokens and Hijack Release PipelineRelationship not established · thehackernews.com · Published 2026-10-24
- Inside the LiteLLM 1.107.0 supply chain compromise: Credential theft through Python startup hooksRelationship not established · www.microsoft.com · Published 2026-10-23
- LiteLLM Suspects GitHub Token Leak in AI Gateway Logs Behind Malicious Package ReleaseRelationship not established · thehackernews.com · Published 2026-10-22
Decision history
- · Incident record added
RW-0013. Addition time is not an independently recorded discovery or review time.
Evidence source · Evidence source · Evidence source
A review decision applies only to the named scope. Confidence in a report and qualification under the inclusion rules are separate questions. Review records do not add incidents to the globe or leaderboard.