CVE-2026-59821

LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks

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.

Scores

Weaknesses (CWE)

• CWE-94

Advisories

• GHSA-72m8-9m7m-h278 — LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks
• PYSEC-2026-3478 — LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks

European references

• ENISA EUVD · EUVD-2026-42350
• GCVE · GCVE-0-2026-59821

Affected configurations (NVD CPE)

• cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:* < 1.82.0
• cpe:2.3:a:litellm:litellm:1.82.0:nightly:*:*:*:*:*:*

Affected products

References

• https://github.com/BerriAI/litellm/security/advisories/GHSA-72m8-9m7m-h278
• https://github.com/BerriAI/litellm/commit/e50b4486d0f7aa0497185a1ebcdd2c91f1769eba
• https://github.com/BerriAI/litellm/releases/tag/v1.82.0-stable

Sources