Vulnerability Description
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.82.0-stable, LiteLLM's Custom Code Guardrails production create and update paths did not apply the same sandboxing and validation used by the test endpoint, allowing a privileged user with access to create or update guardrails to submit custom Python code that executed in the LiteLLM proxy environment and could expose secrets available to the process. This issue is fixed in version 1.82.0-stable.
CVSS Score
HIGH
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Litellm | Litellm | < 1.82.0 |
Related Weaknesses (CWE)
References
- https://github.com/BerriAI/litellm/commit/e50b4486d0f7aa0497185a1ebcdd2c91f1769ePatch
- https://github.com/BerriAI/litellm/releases/tag/v1.82.0-stableProductRelease Notes
- https://github.com/BerriAI/litellm/security/advisories/GHSA-72m8-9m7m-h278MitigationPatchVendor Advisory
FAQ
What is CVE-2026-59821?
CVE-2026-59821 is a vulnerability with a CVSS score of 7.2 (HIGH). LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.82.0-stable, LiteLLM's Custom Code Guardrails production create and update paths did not apply the same...
How severe is CVE-2026-59821?
CVE-2026-59821 has been rated HIGH with a CVSS base score of 7.2/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-59821?
Check the references section above for vendor advisories and patch information. Affected products include: Litellm Litellm.