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.
{
"cna_assigner": "@huntr_ai",
"cwe_ids": [
"CWE-76"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2024/2xxx/CVE-2024-2952.json"
}{
"cpe": "cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:*",
"extracted_events": [
{
"introduced": "0"
},
{
"fixed": "1.34.42"
}
],
"source": [
"CPE_RANGE",
"REFERENCES"
]
}