BerriAI LiteLLM
BerriAI LiteLLM is affected by a high-severity vulnerability (CVE-2026-42271) that is confirmed to be actively exploited in the wild. Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of the product if mitigations are unavailable.
What is this vulnerability?
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.74.2 to before version 1.83.7, two endpoints used to preview an MCP server before saving it — POST /mcp-rest/test/connection and POST /mcp-rest/test/tools/list — accepted a full server configuration in the request body, including the command, args, and env fields used by the stdio transport. When called with a stdio configuration, the endpoints attempted to connect, which spawned the supplied command as a subprocess on the proxy host with the privileges of the proxy process. The endpoints were gated only by a valid proxy API key, with no role check. Any authenticated user — including holders of low-privilege internal-user keys — could therefore run arbitrary commands on the host. This issue has been patched in version 1.83.7.
How it works
This is classified as CWE-77. In plain terms, an attacker could use this flaw in LiteLLM to gain access, disrupt service, or steal data — the exact impact depends on how it’s deployed in your environment.
CVSS vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of the product if mitigations are unavailable.
Mitigations
- Apply the vendor’s security patch or update as soon as it’s available and tested.
- If no patch exists yet, apply the vendor’s temporary workaround.
- Limit network exposure of the affected system until it’s patched.
- Review logs for signs of prior exploitation, especially if it’s flagged for ransomware use.
Recommendations
- Confirm whether BerriAI LiteLLM is used anywhere in your environment.
- Patch internet-facing systems first, then internal ones.
- Set a reminder ahead of the remediation deadline so it doesn’t slip.
- Subscribe to the vendor’s security advisories for earlier warning next time.
Compiled from public threat intelligence (CISA Known Exploited Vulnerabilities catalog and the National Vulnerability Database, referenced in 9 public advisories).