LiteLLM: Server-Side Template Injection in /prompts/test endpoint
CVE-2026-42203 · GHSA-xqmj-j6mv-4862 · published 2026-04-24 · updated 2026-05-12
- Severity
- High
- CVSS score
- 8.6
- Chance of exploitation (EPSS)
- 0.37%
- Fixed in
- 1.83.7
- Exploitation No known exploitation
- Automatable No
- Technical impact Total
- CISA SSVC
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.
Upgrade litellm to 1.83.7 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.
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.
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.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| litellm | PyPI | >= 1.80.5, < 1.83.7 | 1.83.7 |
- CriticalUnauthenticated Remote Code Execution in Langflow via Public Flow Build EndpointlangflowExploited
- CriticalRay is vulnerable to Critical RCE via Safari & Firefox Browsers through DNS Rebinding AttackrayExploited
- CriticalLangflow Unauth RCElangflow, langflow-baseExploited
- CriticalMLflow vulnerable to remote code execution on unauthenticated servers via third-party scorer deserialization importing caller-placed artifacmlflow
- CriticalAgno: Arbitrary code execution via `eval()` on `field_type` in `FunctionCall`agno
- CriticalStorybook: Missing origin validation in Storybook preview allows code injection from malicious websites@storybook/addon-mcp, @storybook/addon-mcp
- CriticalLiteLLM has SQL Injection in Proxy API key verificationlitellmExploited
- HighLiteLLM: MCP Authentication Bypass via OAuth2 Passthrough FallbacklitellmExploited
- HighLiteLLM has a sandbox escape in custom-code guardraillitellmExploited
- HighLiteLLM: Authenticated command execution via MCP stdio test endpointslitellmExploited
- CriticalLiteLLM vulnerable to server-side template injection in the /prompts/test endpointlitellm
- CriticalMalicious code in litellm (PyPI)litellm, litellm, litellm
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.