Intel

AIKIDO-2025-10336

litellm is vulnerable to Exposure of Sensitive Information to an Unauthorized Actor

Exposure of Sensitive Information to an Unauthorized Actor Pre-CVE
Found by Aikido Intel before public disclosure or CVE publication.

40

Medium Risk

This Affects:

Pythonlitellm
1.34.2 - 1.71.1
Fixed in 1.71.2

TL;DR

Affected versions of this package expose sensitive AWS credentials, including aws_access_key_id and aws_secret_access_key, when Litellm reports data to Langfuse during Bedrock API calls. This poses an unnecessary risk as the secrets are processed in cleartext in Langfuse.

Who does this affect?

You are affected if you are using a version that falls within the vulnerable range and if you're using AWS Bedrock with this library.

Background info

litellm is vulnerable to Exposure of Sensitive Information to an Unauthorized Actor in versions 1.34.2 - 1.71.1.

How to fix this

Upgrade the litellm library to the patch version.