AI agent vulnerability · LiteLLM

CVE-2024-10188: LiteLLM Vulnerable to Denial of Service (DoS)

highCVSS 3.0 7.5GHSA-gw2q-qw9j-rgv7

A vulnerability in BerriAI/litellm, as of commit 26c03c9, allows unauthenticated users to cause a Denial of Service (DoS) by exploiting the use of ast.literaleval to parse user input. This function is not safe and is prone to DoS attacks, which can crash the litellm Python server.

Published Mar 20, 2025

Affected packages

litellm

Ecosystem: PyPI
Affected: < 1.53.1.dev1
Fixed in: 1.53.1.dev1
Check: pip show litellm

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

A vulnerability in BerriAI/litellm, as of commit 26c03c9, allows unauthenticated users to cause a Denial of Service (DoS) by exploiting the use of ast.literal_eval to parse user input. This function is not safe and is prone to DoS attacks, which can crash the litellm Python server.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More LiteLLM vulnerabilities

All LiteLLM entries