Browse / AI Framework and Platform Flaws / CVE-2026-59821
LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks
- Class
- AI Framework and Platform Flaws (filed by a model that read the advisory)
- Technique
- Code and command execution
- Affected
- litellm (PyPI)
- Gets past
- Sandbox or allowlist
- CVSS
- CVSS:4.0/AV:N/AC:L/AT:P/PR:H/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N
- EPSS
- 0.9% chance of exploitation in 30 days
How it works, in short
Production create and update routes for custom guardrail code skip the sandbox used by the test endpoint, so submitted Python runs inside the proxy. (Our summary, written by a model. The source text is below.)
Details
Impact
LiteLLM's Custom Code Guardrails production create/update paths did not apply the same sandboxing and validation used by the test endpoint.
A privileged user with access to create or update guardrails could submit custom Python code that executed in the LiteLLM proxy environment. In deployments without a configured master key, callers could be treated as proxy administrators, making this reachable without intended administrative authorization.
This could allow arbitrary code execution in the LiteLLM proxy container and exposure of secrets available to the process.
Patches
The issue is fixed in 1.82.0-stable.
LiteLLM recommend upgrading to 1.82.0-stable or later.
Workarounds
If upgrading is not immediately possible:
- Restrict access to
POST /guardrailsandPUT /guardrails/{guardrail_id}to trusted administrators only. - Ensure
LITELLM_MASTER_KEYis configured. - Avoid enabling Custom Code Guardrails for untrusted users.
References
- https://github.com/BerriAI/litellm/security/advisories/GHSA-72m8-9m7m-h278
- https://nvd.nist.gov/vuln/detail/CVE-2026-59821
- https://github.com/BerriAI/litellm/commit/e50b4486d0f7aa0497185a1ebcdd2c91f1769eba
- https://github.com/BerriAI/litellm
- https://github.com/BerriAI/litellm/releases/tag/v1.82.0-stable
Source: GitHub Advisory Database, used under CC BY 4.0.