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.

There are packages installed that are affected by a vulnerability referenced in the following CVE:

  - 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. (CVE-2026-59821)

ID	Name	Product	Family	Type	Severity
464792	Echo: litellm: security update to 1.82.0	Tenable Cloud Security	Echo Local Security Checks	Local	low
464792	Echo: litellm: security update to 1.82.0	Tenable Self-Hosted Container Security	Echo Local Security Checks	Local	low
445186	SCA: security update for litellm (GHSA-72m8-9m7m-h278)	Tenable Cloud Security	SCA Checks	Local	low
445186	SCA: security update for litellm (GHSA-72m8-9m7m-h278)	Tenable Self-Hosted Container Security	SCA Checks	Local	low

Detections

Analytics

CVE-2026-59821

low

Tenable Plugins

low

low

low

low