# LiteLLM: Authenticated command execution via MCP stdio test endpoints Advisory record · `GHSA-v4p8-mg3p-g94g` - **Identifiers:** `GHSA-v4p8-mg3p-g94g` · `CVE-2026-42271` · `PYSEC-2026-2599` - **State:** Confirmed - **Severity:** CVSS 8.7 High - **Critical:** Yes: KEV, CVSS 7+ and EPSS - **Weakness (CWE):** [CWE-77](https://cwe.mitre.org/data/definitions/77.html) · [CWE-78](https://cwe.mitre.org/data/definitions/78.html) - **Tags:** [Command injection](https://agentprime.io/advisories/tag/command-injection.md) - **Published:** 25 Apr 2026 - **Updated:** 10 Sept 2026 - **Reviewed by a person:** No Published by the GitHub Advisory Database at 25 Apr 2026, 23:27 UTC. agentprime has not analysed this yet, so whether it affects any app is not known. ## Critical Critical, because: - In CISA’s KEV catalogue since 8 Jun 2026: it is known to be exploited. - CVSS score 8.7 (7.0 or more) and EPSS 0.91 (0.1 or more): a high score and a real chance of exploitation in the next 30 days. How we decide what’s critical: ## Affected packages - `litellm` (PyPI): affected `>=1.74.2, <1.83.7`; fixed in `1.83.7` ## Machine-written summary Summary written by Claude Haiku from the source advisory. Not reviewed by a person. > The LiteLLM package (PyPI) versions 1.74.2 up to but not including 1.83.7 are affected. Any authenticated user with a valid proxy API key, including low-privilege internal-user keys, can send a stdio server configuration to the MCP test endpoints and run arbitrary commands on the proxy host with the proxy process's privileges. Upgrade to 1.83.7, which requires the PROXY_ADMIN role for these endpoints; if upgrading is not immediately possible, block the two MCP test endpoints at your reverse proxy or API gateway. Written 1 Nov 2026. ## Not analysed yet We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check. ## Severity and exploitation - 8.7 High, CVSS 4.0: `CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:N/SA:N`, from CNA (GitHub_M) - **CISA KEV:** Listed since 8 Jun 2026: known to be exploited. - **EPSS:** 0.91, the 99th percentile, on 15 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days. ## Timeline - 31 Oct 2026, 14:11 UTC: First seen by agentprime - 31 Oct 2026, 14:11 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-v4p8-mg3p-g94g) ## Sources - [GitHub Advisory Database: GHSA-v4p8-mg3p-g94g](https://github.com/advisories/GHSA-v4p8-mg3p-g94g) - [OSV: GHSA-v4p8-mg3p-g94g](https://osv.dev/vulnerability/GHSA-v4p8-mg3p-g94g) - - - - - Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code. ## Check whether this affects you A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet. - With the agentprime MCP server (), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: - In a browser: reads your lockfile in the browser, never uploading it. - Whether it touches your code, with file and line: the Claude Code plugin, - As JSON: , or `POST https://api.agentprime.io/v1/match` with your packages () --- The web page: . Everything for agents: .