High [CVE-2026-59821] Arbitrary code execution and information disclosure via custom code guardrails
This high-severity Red Hat Linux advisory covers CVE-2026-59821.
Android app · Google Play
Monitor future Red Hat Linux CVEs from your phone.
Choose a whole vendor or a precise platform, then receive matching security advisories by phone notification, email, or both. Coverage follows 32 official vendor sources and 160+ reviewed platform categories.
Summary
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. A flaw was found in LiteLLM, a proxy server for Large Language Model (LLM) APIs.
The flaw allowed the user to submit custom Python code that would execute within the LiteLLM proxy environment, potentially exposing sensitive information or secrets accessible to the process. Red Hat rates this flaw with higher severity than the upstream GitHub Security Advisory (GHSA-72m8-9m7m-h278, CVSS v4.0 2.1, Low).
Red Hat scored this CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:H (7.2, Important) because a successful exploit grants arbitrary Python code execution within the LiteLLM proxy process, resulting in full compromise of the confidentiality, integrity, and availability of that component, including exposure of any secrets accessible to the process.
- < 1.82.0-stable
Official advisory · high-confidence parse· fetched 12 days ago·verify at source
- 1.82.0
- 1.82.0-stable
Official advisory · high-confidence parse· fetched 12 days ago·verify at source
Mitigation checklist
- Upgrade litellm to 1.82.0 or later, which enforces the same code-safety checks on the guardrail create/update endpoints as the test endpoint. If upgrading is not immediately possible, restrict access to POST /guardrails and PUT /guardrails/{guardrail_id} to trusted administrators only, ensure LITELLM_MASTER_KEY is configured so unauthenticated callers are not treated as proxy administrators, and avoid enabling Custom Code Guardrails for untrusted users.
Official advisory · high-confidence parse· fetched 12 days ago·verify at source
Discussion(0)
No comments yet. Share field notes, upgrade gotchas, or questions — verify against the vendor advisory before acting on community advice.
Sign in to join the discussion.