LowGHSA-72m8-9m7m-h278CVE-2026-59821PYSEC-2026-3478

LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks

Published 22 Jul 2026 · Updated 10 Sept 2026

Is your project on an affected litellm?

Private repo? Upload its lockfile instead, or connect GitHub to check every repo.

Look after several Python apps? Indie watches up to 15 repos, private ones too, for $5 a month. See Indie

Affected package

Affected
<1.82.0
Fixed in
1.82.0
Update to the fixed version for your release line, for example:pip install 'litellm>=1.82.0'

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:

1. Restrict access to POST /guardrails and PUT /guardrails/{guardrail_id} to trusted administrators only. 2. Ensure LITELLM_MASTER_KEY is configured. 3. Avoid enabling Custom Code Guardrails for untrusted users.

Is GHSA-72m8-9m7m-h278 in any of your client repos?

Checking one package by hand is fine. Checking it across forty client projects is not. NPMscan reads the lockfiles in every GitHub repo you pick, finds each project with an affected litellm, and gives you the command that fixes it.

More advisories for litellm

  • HighGHSA-g5ff-637f-6q2mLiteLLM: internal_user_viewer arbitrary local file read via `vertex_ai_credentials` · 27 Oct 2026
  • MediumGHSA-hhww-mrg2-969hLiteLLM vulnerable to reflected XSS in /sso/debug/callback · 27 Oct 2026
  • HighCVE-2026-114612LiteLLM: Privilege Escalation to Proxy Admin via Cross-Domain Reuse of the Salt Key · 27 Oct 2026
  • MediumCVE-2026-84377LiteLLM: Authenticated SSRF and provider-credential exfiltration via unvalidated request-body routing parameters · 30 Sept 2026
  • MediumCVE-2026-59823LiteLLM Proxy has server-side request forgery via the `user_config` request parameter · 17 Sept 2026
  • CriticalCVE-2026-37004LiteLLM vulnerable to server-side template injection in the /prompts/test endpoint · 27 Aug 2026
All 45 advisories for litellm

References

Advisory data from OSV.dev (opens OSV.dev in a new tab), refreshed daily.