AI and data stack advisories

Severe, 6 weeks1496Projects326

1496 severe, 6 weeks · 326 projects

LiteLLMGHSA-g26j-5385-hhw3

LiteLLM Server-Side Request Forgery (SSRF) vulnerability

LiteLLM

CVE-2024-6587 · Published Sep 13, 2024 · updated Sep 10, 2026

High7.5
Fix: upgrade to 1.44.8 or later
GitHub advisory

A Server-Side Request Forgery (SSRF) vulnerability exists in berriai/litellm version 1.38.10. This vulnerability allows users to specify the api_base parameter when making requests to POST /chat/completions, causing the application to send the request to the domain specified by api_base. This request includes the OpenAI API key. A malicious user can set the api_base to their own domain and intercept the OpenAI API key, leading to unauthorized access and potential misuse of the API key.

Affected versions

PackageAffectedFixed in
litellm
PyPI
< 1.44.81.44.8
Details and references
CVSS 3.0
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Severity from
GitHub (reviewed advisory)
Weakness
CWE-918
Also known as
CVE-2024-6587, PYSEC-2026-1547

More LiteLLM advisories

All LiteLLM
Critical 9.8Jun 27, 2024litellm vulnerable to remote code execution based on using eval unsafelyCVE-2024-5751fixed in 1.40.16Medium 5.3Jun 27, 2024litellm vulnerable to improper access control in team managementCVE-2024-5710fixed in 1.40.15High 6.5Jun 6, 2024Arbitrary file deletion in litellmCVE-2024-4888fixed in 1.35.36Medium 4.9Jun 6, 2024SQL injection in litellmCVE-2024-4890no fix yetMedium 6.4Jun 6, 2024SQL injection in litellmCVE-2024-5225fixed in 1.40.0High 7.2May 18, 2024litellm passes untrusted data to `eval` function without sanitizationCVE-2024-4264no fix yet