Overview
- 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.
- Source
- security@huntr.dev
- NVD status
- Awaiting Analysis
Risk scores
CVSS 3.0
- Type
- Secondary
- Base score
- 9.8
- Impact score
- 5.9
- Exploitability score
- 3.9
- Vector string
- CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- Severity
- CRITICAL
Weaknesses
- security@huntr.dev
- CWE-76
Social media
- Hype score
- Not currently trending