CVE-2026-59821
Published:July 08, 2026
Updated:August 04, 2026
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.
Affected Packages
litellm (CONDA):
Affected version(s) >=1.34.0 <1.82.0Fix Suggestion:
Update to version 1.82.0litellm (CONDA):
Affected version(s) >=1.34.0 <1.82.0Fix Suggestion:
Update to version 1.82.0litellm (PYTHON):
Affected version(s) >=0.1.0 <1.82.0Fix Suggestion:
Update to version 1.82.0litellm (PYTHON):
Affected version(s) >=0.1.0 <1.82.0Fix Suggestion:
Update to version 1.82.0Related Resources (8)
Do you need more information?
Contact UsCVSS v4
Base Score:
2.1
Attack Vector
NETWORK
Attack Complexity
LOW
Attack Requirements
PRESENT
Privileges Required
HIGH
User Interaction
NONE
Vulnerable System Confidentiality
LOW
Vulnerable System Integrity
LOW
Vulnerable System Availability
LOW
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
4.7
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
HIGH
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
LOW
Integrity
LOW
Availability
LOW
Weakness Type (CWE)
Improper Control of Generation of Code ('Code Injection')
EPSS
Base Score:
0.36