CVE-2024-2952: LiteLLM has Server-Side Template Injection vulnerability in /completions endpoint
(updated )
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
- github.com/BerriAI/litellm
- github.com/BerriAI/litellm/blob/0d803e13798db40aa7463e64a6bafaee386424f5/litellm/proxy/proxy_server.py
- github.com/BerriAI/litellm/commit/8a1cdc901708b07b7ff4eca20f9cb0f1f0e8d0b3
- github.com/BerriAI/litellm/issues/2949
- github.com/BerriAI/litellm/pull/2941
- github.com/advisories/GHSA-46cm-pfwv-cgf8
- github.com/pypa/advisory-database/tree/main/vulns/litellm/PYSEC-2026-387.yaml
- huntr.com/bounties/a9e0a164-6de0-43a4-a640-0cbfb54220a4
- nvd.nist.gov/vuln/detail/CVE-2024-2952
- pypi.org/project/litellm
Code Behaviors & Features
Detect and mitigate CVE-2024-2952 with GitLab Dependency Scanning
Secure your software supply chain by verifying that all open source dependencies used in your projects contain no disclosed vulnerabilities. Learn more about Dependency Scanning →