Two LiteLLM releases on PyPI carried a credential stealer after a CI tool breach
LiteLLM versions 1.82.7 and 1.82.8, uploaded to PyPI on March 24, 2026, contained code that collected environment variables, SSH keys, cloud and Kubernetes credentials and database passwords, then encrypted and sent them to a lookalike domain. LiteLLM believes the attacker used credentials stolen through the earlier Trivy compromise to publish directly to PyPI. The official proxy Docker image was not affected.
Sources
- Primary: https://docs.litellm.ai/blog/security-update-march-2026
- Upstream: Editorial
- Entered by the cybermap.lol editors, with sources on the entry
Defenses for this class of incident
all categoriesA supply chain sits in these classes of the AI-security landscape. The companies below work on that class of problem. This is a taxonomy, not a claim that any of them would have changed this incident.
Vendor data: AI Security Startups Map by Prompt Security (CC BY 4.0), synced daily. startups.prompt.security. Paid placements are labelled Sponsored; HeimWall, which runs this site, is labelled Operator. 453 companies in the directory.
Wrong or missing? Email founders@heimwall.ai. Corrections are logged here, in place. How corrections and takedowns work.