RCE in Berriai Litellm
CVE-2026-59821
- CVSS v3
- 7.2 High
- Public exploits
- None known
- EPSS
- 0.009 · 60.7th percentile
- Published
- 2026-07-08
What to do
- Fixed in
1.82.0-stable- Affected
- 2 affected products
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.
Vulnerability class: RCE (Remote Code Execution)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 7.2 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:H.
- Attack Vector
- Network
AV:N - Attack Complexity
- Low
AC:L - Privileges Required
- High
PR:H - User Interaction
- None
UI:N - Scope
- Unchanged
S:U - Confidentiality
- High
C:H - Integrity
- High
I:H - Availability
- High
A:H
EPSS exploit prediction
EPSS 0.009, 60.7th percentile (last changed ); unchanged over 30 days. About EPSS.
Affected products
- Berriai Litellm — versions < 1.82.0-stable
- Litellm — versions 1.82.0
Weakness classification (CWE)
References
- https://github.com/BerriAI/litellm/security/advisories/GHSA-72m8-9m7m-h278 (Patch, Mitigation, Vendor Advisory)
- https://github.com/BerriAI/litellm/commit/e50b4486d0f7aa0497185a1ebcdd2c91f1769eba (Patch)
- https://github.com/BerriAI/litellm/releases/tag/v1.82.0-stable (Product, Release Notes)