CVE-2024-2952— Server-Side Template Injection in BerriAI/litellm
Quick assessment
Affected
berriai berriai/litellm
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.
LiteLLM是Berri AI开源的一个应用程序。可以使用 OpenAI 格式调用所有 LLM API。 LiteLLM存在安全漏洞，该漏洞源于对文件参数没有进行适当的清理，容易受到服务器端模板注入(SSTI)攻击。
Possible ATT&CK Techniques 1 AI
T1190 · Exploit Public-Facing Application
Get alerts for future matching vulnerabilities
Log in to subscribe
I. Basic Information for CVE-2024-2952
Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
Vulnerability Title
Server-Side Template Injection in BerriAI/litellm
Source: CVE Program / CVE List V5
Vulnerability 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: CVE Program / CVE List V5
CVSS Information
N/A
Source: CVE Program / CVE List V5
Vulnerability Type
等价特殊元素的转义处理不恰当
Source: CVE Program / CVE List V5
Vulnerability Title
LiteLLM 安全漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
LiteLLM是Berri AI开源的一个应用程序。可以使用 OpenAI 格式调用所有 LLM API。 LiteLLM存在安全漏洞，该漏洞源于对文件参数没有进行适当的清理，容易受到服务器端模板注入(SSTI)攻击。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)
Affected Products
| Vendor | Product | Affected Versions | CPE | Subscribe |
|---|---|---|---|---|
| berriai | berriai/litellm | unspecified ~ 1.34.42 | - |
|
II. Public POCs for CVE-2024-2952
| # | POC Description | Source Link | Shenlong Link |
|---|
AI-Generated POC
Premium
No public POC found.
Login to generate AI POCIII. Intelligence Information for CVE-2024-2952
请登录查看更多情报信息。
Patches & Fixes for CVE-2024-2952 (1)
Vendor Advisories for CVE-2024-2952 (1)
IV. Related Vulnerabilities
Same product: berriai/litellm
-
CVE-2024-6825
Remote Code Execution in BerriAI/litellm -
CVE-2024-10188
Denial of Service in BerriAI/litellm -
CVE-2025-0628
Improper Authorization in BerriAI/litellm -
CVE-2025-0330
Exposure of Sensitive Information in berriai/litellm -
CVE-2024-9606
Improper Output Neutralization for Logs in berriai/litellm
Same vendor: berriai
-
CVE-2026-59819
LiteLLM: Local file read via request-supplied OIDC file refe -
CVE-2026-59822
LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fa -
CVE-2026-59820
LiteLLM: Improper Limitation of a Pathname to a Restricted D -
CVE-2026-59821
LiteLLM: Custom Code Guardrails production endpoints bypass -
CVE-2026-49468
LiteLLM: Authentication Bypass via Host Header Injection
Same weakness: CWE-76
-
CVE-2026-54722
dssrf: there a critical security bug with remove_at_symbol_i -
CVE-2026-55723
NGINX Ingress Controller vulnerability -
CVE-2026-11311
NGINX Gateway Fabric vulnerability -
CVE-2024-4897
Remote Code Execution in parisneo/lollms-webui -
CVE-2024-34359
llama-cpp-python vulnerable to Remote Code Execution by Serv
V. Comments for CVE-2024-2952
No comments yet