Two LiteLLM versions published containing credential harvesting malware
GHSA-5mg7-485q-xm76 · published 2026-03-25 · updated 2026-03-27
- Severity
- Critical
- CVSS score
- Not scored
- Chance of exploitation (EPSS)
- No CVE
- Fixed in
- No fix yet
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.
No fixed release is listed yet for litellm. Follow the source advisory for updates, and until one ships:
General guidance from ShieldPi, not a vendor fix
- Compromised release. Move to a release the advisory names as clean, and rotate every credential, token and key the environment that ran the affected release could read.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| litellm | PyPI | >= 1.82.7, <= 1.82.8 | No fix yet |
- CriticalMalicious code in guardrails-ai 0.10.1 (supply chain compromise)guardrails-ai
- CriticalMalicious dropper in mistralai 2.4.6 PyPI packagemistralai
- CriticalCompromise of PyTorch Lightning PyPi Package Versionspytorch-lightning, pytorch-lightning
- CriticalLiteLLM has SQL Injection in Proxy API key verificationlitellmExploited
- HighLiteLLM: MCP Authentication Bypass via OAuth2 Passthrough FallbacklitellmExploited
- HighLiteLLM has a sandbox escape in custom-code guardraillitellmExploited
- HighLiteLLM: Authenticated command execution via MCP stdio test endpointslitellmExploited
- CriticalLiteLLM vulnerable to server-side template injection in the /prompts/test endpointlitellm
- CriticalMalicious code in litellm (PyPI)litellm, litellm, litellm
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.