{"id":"CVE-2026-31945","aliases":["EUVD-2026-16765","GHSA-f92m-jpv7-55p2"],"status":"published","title":"LibreChat Server-Side Request Forgery using DNS resolution","description":"LibreChat is a ChatGPT clone with additional features. Versions 0.8.2-rc2 through 0.8.2 are vulnerable to a server-side request forgery (SSRF) attack when using agent actions or MCP. Although a previous SSRF vulnerability (https://github.com/danny-avila/LibreChat/security/advisories/GHSA-rgjq-4q58-m3q8) was reported and patched, the fix only introduced hostname validation. It does not verify whether DNS resolution results in a private IP address. As a result, an attacker can still bypass the protection and gain access to internal resources, such as an internal RAG API or cloud instance metadata endpoints. Version 0.8.3-rc1 contains a patch.","severity":{"version":"3.1","score":7.7,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N","level":"high","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-10","score":0.00259,"percentile":0.17695,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":false},"cwes":["CWE-918"],"published":"2026-03-27T19:23:53Z","modified":"2026-10-28T02:30:24Z","products":[{"vendor":"danny-avila","product":"librechat"},{"vendor":"librechat","product":"librechat"}],"references":[{"url":"https://github.com/danny-avila/LibreChat/security/advisories/GHSA-f92m-jpv7-55p2","tags":["x_refsource_CONFIRM","exploit","Exploit","Mitigation","Vendor Advisory","advisory"]},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/31xxx/CVE-2026-31945.json","tags":["advisory"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-31945","tags":["advisory"]}],"sources":{"cve":[{"id":"CVE-2026-31945","title":"LibreChat Server-Side Request Forgery using DNS resolution","description":"LibreChat is a ChatGPT clone with additional features. Versions 0.8.2-rc2 through 0.8.2 are vulnerable to a server-side request forgery (SSRF) attack when using agent actions or MCP. Although a previous SSRF vulnerability (https://github.com/danny-avila/LibreChat/security/advisories/GHSA-rgjq-4q58-m3q8) was reported and patched, the fix only introduced hostname validation. It does not verify whether DNS resolution results in a private IP address. As a result, an attacker can still bypass the protection and gain access to internal resources, such as an internal RAG API or cloud instance metadata endpoints. Version 0.8.3-rc1 contains a patch.","status":"published","published":"2026-03-27T19:23:53.395Z","modified":"2026-03-30T19:00:53.475Z","cvss":[{"version":"3.1","score":7.7,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N","level":"high","assessor":"cna"}],"cwes":["CWE-918"],"updated_at":"2026-11-02T14:19:50.92611Z"}],"euvd":[{"id":"EUVD-2026-16765","description":"LibreChat is a ChatGPT clone with additional features. Versions 0.8.2-rc2 through 0.8.2 are vulnerable to a server-side request forgery (SSRF) attack when using agent actions or MCP. Although a previous SSRF vulnerability (https://github.com/danny-avila/LibreChat/security/advisories/GHSA-rgjq-4q58-m3q8) was reported and patched, the fix only introduced hostname validation. It does not verify whether DNS resolution results in a private IP address. As a result, an attacker can still bypass the protection and gain access to internal resources, such as an internal RAG API or cloud instance metadata endpoints. Version 0.8.3-rc1 contains a patch.","status":"published","published":"2026-03-27T19:23:53Z","modified":"2026-03-30T19:00:53Z","cvss":[{"version":"3.1","score":7.7,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N","level":"high"}],"updated_at":"2026-11-02T19:25:25.377294Z"}],"nvd":[{"id":"CVE-2026-31945","description":"LibreChat is a ChatGPT clone with additional features. Versions 0.8.2-rc2 through 0.8.2 are vulnerable to a server-side request forgery (SSRF) attack when using agent actions or MCP. Although a previous SSRF vulnerability (https://github.com/danny-avila/LibreChat/security/advisories/GHSA-rgjq-4q58-m3q8) was reported and patched, the fix only introduced hostname validation. It does not verify whether DNS resolution results in a private IP address. As a result, an attacker can still bypass the protection and gain access to internal resources, such as an internal RAG API or cloud instance metadata endpoints. Version 0.8.3-rc1 contains a patch.","status":"published","published":"2026-03-27T20:16:30.06Z","modified":"2026-10-26T21:10:00.17Z","cvss":[{"version":"3.1","score":7.7,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N","level":"high","assessor":"secondary"}],"cwes":["CWE-918"],"updated_at":"2026-11-02T14:12:11.678711Z"}],"osv":[{"id":"CVE-2026-31945","title":"LibreChat Server-Side Request Forgery using DNS resolution","description":"LibreChat is a ChatGPT clone with additional features. Versions 0.8.2-rc2 through 0.8.2 are vulnerable to a server-side request forgery (SSRF) attack when using agent actions or MCP. Although a previous SSRF vulnerability (https://github.com/danny-avila/LibreChat/security/advisories/GHSA-rgjq-4q58-m3q8) was reported and patched, the fix only introduced hostname validation. It does not verify whether DNS resolution results in a private IP address. As a result, an attacker can still bypass the protection and gain access to internal resources, such as an internal RAG API or cloud instance metadata endpoints. Version 0.8.3-rc1 contains a patch.","status":"published","published":"2026-03-27T19:23:53.395Z","modified":"2026-10-28T02:30:24.535228993Z","cvss":[{"version":"3.1","score":7.7,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N","level":"high"}],"cwes":["CWE-918"],"updated_at":"2026-11-02T15:45:01.218144Z"}]}}