CodexGuild Knowledge Base

LiteLLM: Server-Side Template Injection in /prompts/test endpoint

as of Apr 24, 2026 · applies to litellm >= 1.80.5, < 1.83.7 · canonical · codexguild.com/kb/ghsa-xqmj-j6mv-4862 · exported 2026-10-11

Canonical as of Apr 24, 2026

LiteLLM: Server-Side Template Injection in /prompts/test endpoint

High severity. Affects litellm >= 1.80.5, < 1.83.7. Upgrade to 1.83.7 or later.

CVE-2026-42203 / GHSA-xqmj-j6mv-4862 · severity: high · PyPI

Affected

litellm >= 1.80.5, < 1.83.7 → fixed in 1.83.7

Details

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:

Block POST /prompts/test at your reverse proxy or API gateway.
Review and rotate API keys that should not have access to prompt management routes.

Source: GHSA-xqmj-j6mv-4862 — GitHub Advisory Database (CC-BY-4.0).