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"
}{
"extracted_events": [
{
"cpe": "cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:*",
"range": [
{
"introduced": "0"
},
{
"fixed": "1.34.42"
}
],
"source": "CPE_RANGE"
},
{
"range": [
{
"fixed": "8a1cdc901708b07b7ff4eca20f9cb0f1f0e8d0b3"
}
],
"source": "REFERENCES_COMMIT"
}
]
}