Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-42203— LiteLLM: Server-Side Template Injection in /prompts/test endpoint

Quick assessment

Affected
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 1.80.5版本至1.83.7之前版本存在安全漏洞，该漏洞源于POST /prompts/test端点接受用户提供的提示模板且无沙箱渲染，可能导致特制模板在LiteLLM代理进程中运行任意代码，任何拥有有效代理API密钥的认证用户均可利用，可能暴露进程环境中的秘密并允许在主机上运行命令。

AI Predicted 9.8 Difficulty: Easy EPSS 0.66% · P50

Affected Version Matrix 1

VendorProduct Version RangeStatus
BerriAI litellm >= 1.80.5, < 1.83.7 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-42203

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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
LiteLLM: Server-Side Template Injection in /prompts/test endpoint
Source: CVE Program / CVE List V5
Vulnerability Description
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.80.5 to before version 1.83.7, the POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the LiteLLM Proxy process. The endpoint only checks that the caller presents a valid proxy API key, so any authenticated user could reach it. Depending on how the proxy is deployed, this could expose secrets in the process environment (such as provider API keys or database credentials) and allow commands to be run on the host. This issue has been patched in version 1.83.7.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N
Source: CVE Program / CVE List V5
Vulnerability Type
CWE-1336
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 1.80.5版本至1.83.7之前版本存在安全漏洞，该漏洞源于POST /prompts/test端点接受用户提供的提示模板且无沙箱渲染，可能导致特制模板在LiteLLM代理进程中运行任意代码，任何拥有有效代理API密钥的认证用户均可利用，可能暴露进程环境中的秘密并允许在主机上运行命令。
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 litellm >= 1.80.5, < 1.83.7 -

II. Public POCs for CVE-2026-42203

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-42203

请登录查看更多情报信息。

Vendor Advisories for CVE-2026-42203 (1)

Vendor Pages for CVE-2026-42203 (1)

Same Patch Batch · BerriAI · 2026-05-08 · 3 CVEs total

CVE-2026-42271 LiteLLM: Authenticated command execution via MCP stdio test endpoints
CVE-2026-42208 LiteLLM: SQL injection in Proxy API key verification

IV. Related Vulnerabilities

Same product: litellm
Same vendor: BerriAI
Same weakness: CWE-1336

V. Comments for CVE-2026-42203

No comments yet

Leave a comment