berriai/litellm · Security
LiteLLM has a sandbox escape in custom-code guardrail
- GHSA ID
- GHSA-wxxx-gvqv-xp7p
- CVE ID
- CVE-2026-40217
- Severity
- high
- Published
- Updated
- CVSS
- 8.8 · CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
- CVSS v3
- 8.8 · CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
- CVSS v4
- 7.5 · CVSS:4.0/AV:N/AC:H/AT:N/PR:H/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Description
Impact
The POST /guardrails/test_custom_code endpoint runs user-supplied Python inside a hand-rolled sandbox. The sandbox can be escaped using bytecode-level techniques, allowing arbitrary code execution in the proxy process — which runs as root in the default Docker image.
Reaching the endpoint requires a proxy-admin credential in default configurations.
Patches
Fixed in 1.83.11. The hand-rolled sandbox has been replaced with RestrictedPython. Upgrade to 1.83.11 or later.
Workarounds
If upgrading is not immediately possible, block POST /guardrails/test_custom_code at your reverse proxy or API gateway.
References
- Patched release:
v1.83.10-stable
CWEs
- CWE-420 · Unprotected Alternate Channel
- CWE-913 · Improper Control of Dynamically-Managed Code Resources
References
- https://github.com/BerriAI/litellm/security/advisories/GHSA-wxxx-gvqv-xp7p ↗
- https://nvd.nist.gov/vuln/detail/CVE-2026-40217 ↗
- https://github.com/BerriAI/litellm/releases/tag/v1.83.10-stable ↗
- https://www.x41-dsec.de/lab/advisories/x41-2026-001-litellm ↗
- https://github.com/advisories/GHSA-wxxx-gvqv-xp7p ↗