LiteLLM has Server-Side Template Injection vulnerability in /completions endpoint
GHSA-46cm-pfwv-cgf8 · CVE-2024-2952 · PYSEC-2026-387
Published · Modified
AI SAST
Find this class of vulnerability in your own code
Corgea's AI-native static analysis detects vulnerabilities like this one across your repositories, ranks them by exploitability, and returns review-ready fixes.
Description
BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the /completions endpoint. The vulnerability arises from the hf_chat_template method processing the chat_template parameter from the tokenizer_config.json file through the Jinja template engine without proper sanitization. Attackers can exploit this by crafting malicious tokenizer_config.json files that execute arbitrary code on the server.
References
- ADVISORY https://nvd.nist.gov/vuln/detail/CVE-2024-2952
- WEB https://github.com/BerriAI/litellm/issues/2949
- WEB https://github.com/BerriAI/litellm/pull/2941
- WEB https://github.com/BerriAI/litellm/commit/8a1cdc901708b07b7ff4eca20f9cb0f1f0e8d0b3
- PACKAGE https://github.com/BerriAI/litellm
- WEB https://github.com/BerriAI/litellm/blob/0d803e13798db40aa7463e64a6bafaee386424f5/litellm/proxy/proxy_server.py#L2087
- ADVISORY https://github.com/advisories/GHSA-46cm-pfwv-cgf8
- WEB https://github.com/pypa/advisory-database/tree/main/vulns/litellm/PYSEC-2026-387.yaml
- WEB https://huntr.com/bounties/a9e0a164-6de0-43a4-a640-0cbfb54220a4
- WEB https://pypi.org/project/litellm
Ready to move
Start Securing
Free, no credit card | First findings in minutes