{"id":"CVE-2026-22252","url":"https://www.cyber-defence.io/tools/cve/CVE-2026-22252","generatedAt":"2026-10-28T03:32:19.821Z","title":"Prior to v0.8.2-rc2, LibreChat's MCP stdio transport accepts arbitrary commands without validation, allowing any authenticated user to execute shell commands as root inside the container through a single API request.","description":"LibreChat is a ChatGPT clone with additional features. Prior to v0.8.2-rc2, LibreChat's MCP stdio transport accepts arbitrary commands without validation, allowing any authenticated user to execute shell commands as root inside the container through a single API request. This vulnerability is fixed in v0.8.2-rc2.","published":"2026-01-12T19:16:03.000Z","lastModified":"2026-06-17T10:19:38.000Z","status":"Analyzed","sourceIdentifier":"security-advisories@github.com","cvss":{"version":"3.1","score":9.9,"severity":"CRITICAL","vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H"},"cwe":["CWE-285"],"affected":["librechat/librechat"],"epss":{"score":0.04223,"percentile":0.90948,"date":"2026-10-27","history":[]},"kev":{"listed":false},"exploits":{"count":0,"verified":false,"firstPublished":null,"source":"Exploit-DB (https://gitlab.com/exploit-database/exploitdb)","entries":[]},"verdict":{"level":"high","text":"High impact if exploited, but EPSS currently rates exploitation as unlikely (4.22%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit."},"changes":[],"references":[{"url":"https://github.com/danny-avila/LibreChat/commit/211b39f3113d4e6ecab84be0a83f4e9c9dea127f","tags":["Patch"],"source":"security-advisories@github.com"},{"url":"https://github.com/danny-avila/LibreChat/security/advisories/GHSA-cxhj-j78r-p88f","tags":["Exploit","Vendor Advisory"],"source":"security-advisories@github.com"}],"sources":{"nvd":"https://nvd.nist.gov/vuln/detail/CVE-2026-22252","epss":"https://www.first.org/epss/","kev":"https://www.cisa.gov/known-exploited-vulnerabilities-catalog","exploitdb":"https://www.exploit-db.com/"},"licence":"CC BY 4.0 — link back to the CVE Explorer if you publish the results; upstream data remains subject to its own terms."}