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.
AI analysis not yet available
Plain-English explanation, risk summary, and remediation steps will appear here once AI analysis is complete.
No Fix Known
No patch has been released yet. Apply workarounds or mitigations where available.
Published
CVE disclosed publicly
Last Modified
Most recent update
Indexed to CVEInsight
Added to this platform
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
1
Affected Products
4
References
litellm / litellm
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Exploitability
Impact