CVE-2026-42203

描述

### Impact 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. Proxy deployments running an affected version are in scope. ### Patches The issue is fixed in **`1.83.7-stable`**. The fix switches the prompt template renderer to a sandboxed environment that blocks the attributes this attack relies on. LiteLLM recommends upgrading to `1.83.7-stable` or later. ### Workarounds If upgrading is not immediately possible: 1. Block `POST /prompts/test` at your reverse proxy or API gateway. 2. Review and rotate API keys that should not have access to prompt management routes.

如何修補 CVE-2026-42203

要修補 CVE-2026-42203,請將受影響套件升級到下列已修補版本。

• —升級至 1.83.7 或更新版本
• —升級至 1.83.7 或更新版本

CVE-2026-42203 正在被利用嗎?

低 — EPSS 為 0.4%,目前沒有觀察到大規模利用活動。

受影響套件(2)

• >= 1.80.5, < 1.83.7
• >= 1.80.5, < 1.83.7

CVSS 分數

參考連結(6)

• ADVISORYgithub.com/advisories/GHSA-xqmj-j6mv-4862
• ADVISORYnvd.nist.gov/vuln/detail/CVE-2026-42203
• PATCHgithub.com/BerriAI/litellm
• PATCHpypi.org/project/litellm
• WEBgithub.com/BerriAI/litellm/releases/tag/v1.83.7-stable