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.
Attack Parameters
Attack Vector
Network
Can be exploited remotely
Attack Complexity
Low
Easy to exploit
Attack Requirements
Present
Additional conditions required
Privileges Required
High
Admin privileges needed
User Interaction
None
No user interaction needed
Impact Assessment
Confidentiality
Low
Partial data leak
Integrity
Low
Partial data modification
Availability
Low
Partial disruption
CVSS Vector v4.0
Weakness Type (CWE)
Vulnerable Products 2
| Configuration | From (including) | Up to (excluding) |
|---|---|---|
|
Litellm Litellm
cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:*
|
— |
1.82.0
|
|
Litellm Litellm
cpe:2.3:a:litellm:litellm:1.82.0:nightly:*:*:*:*:*:*
|
— | — |
References 3
https://github.com/BerriAI/litellm/commit/e50b4486d0f7aa0497185a1ebcdd2c91f1769…
security-advisories@github.com
https://github.com/BerriAI/litellm/releases/tag/v1.82.0-stable
security-advisories@github.com
https://github.com/BerriAI/litellm/security/advisories/GHSA-72m8-9m7m-h278
security-advisories@github.com