AI agent vulnerability · LiteLLM

GHSA-5mg7-485q-xm76: Two LiteLLM versions published containing credential harvesting malware

critical

After an API Token exposure from an exploited trivy dependency, two new releases of litellm were uploaded to PyPI containing automatically activated malware, harvesting sensitive credentials and files, and exfiltrating to a remote API. Anyone who has installed and run the project should assume any credentials available to litellm environment may have been exposed, and revoke/rotate thema ccordingly.

Published Mar 25, 2026 · Updated Mar 27, 2026

Affected packages

litellm

Ecosystem: PyPI
Affected: >= 1.82.7, <= 1.82.8
Fixed in: No patched version yet
Check: pip show litellm

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

After an API Token exposure from an exploited trivy dependency, two new releases of litellm were uploaded to PyPI containing automatically activated malware, harvesting sensitive credentials and files, and exfiltrating to a remote API.

Anyone who has installed and run the project should assume any credentials available to litellm environment may have been exposed, and revoke/rotate thema ccordingly.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More LiteLLM vulnerabilities

All LiteLLM entries