{"id":"CVE-2026-63764","aliases":["EUVD-2026-46412","GHSA-rqhf-rg9p-w5gg"],"status":"published","title":"LMDeploy Server-Side Request Forgery via HTTP Redirect Bypass","description":"LMDeploy through 0.14.0, fixed in commit 03c3130, contains a server-side request forgery (SSRF) vulnerability in the _load_http_url function within the connection.py media handler, where the private-IP guard validates only the original URL without re-validating hosts after HTTP redirects. An unauthenticated attacker can submit a crafted image_url to the chat completions endpoint pointing to an attacker-controlled host that returns a redirect to a private IP or cloud-metadata endpoint, causing the server to follow the redirect and expose internal service content through the model pipeline.","severity":{"version":"4.0","score":7.7,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:N/SC:H/SI:N/SA:N","level":"high","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-12","score":0.00511,"percentile":0.44138,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":false},"cwes":["CWE-918"],"published":"2026-07-21T20:36:58Z","modified":"2026-10-28T02:31:09Z","products":[{"vendor":"internlm","product":"lmdeploy"}],"references":[{"url":"https://github.com/InternLM/lmdeploy/issues/4761","tags":["technical-description","exploit","issue-tracking","Exploit","Issue Tracking","Mitigation","report"]},{"url":"https://github.com/InternLM/lmdeploy/pull/4734","tags":["issue-tracking","patch","Issue Tracking","Patch","fix"]},{"url":"https://github.com/InternLM/lmdeploy/commit/03c313006d17cc3feae86b633c44206a997c44db","tags":["patch","Patch","fix"]},{"url":"https://www.vulncheck.com/advisories/lmdeploy-server-side-request-forgery-via-http-redirect-bypass","tags":["third-party-advisory","Exploit","Patch","Third Party Advisory","advisory"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-63764","tags":["advisory"]},{"url":"https://github.com/InternLM/lmdeploy","tags":["package"]},{"url":"https://www.vulncheck.com/advisories/lmdeploy-server-side-request-forgery-via-http-redirect-bypass-of-private-ip-guard-in-vision-image-fetch"},{"url":"https://github.com/advisories/GHSA-rqhf-rg9p-w5gg"},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/63xxx/CVE-2026-63764.json","tags":["advisory"]}],"sources":{"cve":[{"id":"CVE-2026-63764","title":"LMDeploy Server-Side Request Forgery via HTTP Redirect Bypass","description":"LMDeploy through 0.14.0, fixed in commit 03c3130, contains a server-side request forgery (SSRF) vulnerability in the _load_http_url function within the connection.py media handler, where the private-IP guard validates only the original URL without re-validating hosts after HTTP redirects. An unauthenticated attacker can submit a crafted image_url to the chat completions endpoint pointing to an attacker-controlled host that returns a redirect to a private IP or cloud-metadata endpoint, causing the server to follow the redirect and expose internal service content through the model pipeline.","status":"published","published":"2026-07-21T20:36:58.372Z","modified":"2026-09-17T18:57:27.785Z","cvss":[{"version":"4.0","score":7.7,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:N/SC:H/SI:N/SA:N","level":"high","assessor":"cna"},{"version":"3.1","score":8.6,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N","level":"high","assessor":"cna"}],"cwes":["CWE-918"],"updated_at":"2026-11-02T14:19:56.284359Z"}],"euvd":[{"id":"EUVD-2026-46412","description":"LMDeploy through 0.14.0, fixed in commit 03c3130, contains a server-side request forgery (SSRF) vulnerability in the _load_http_url function within the connection.py media handler, where the private-IP guard validates only the original URL without re-validating hosts after HTTP redirects. An unauthenticated attacker can submit a crafted image_url to the chat completions endpoint pointing to an attacker-controlled host that returns a redirect to a private IP or cloud-metadata endpoint, causing the server to follow the redirect and expose internal service content through the model pipeline.","status":"published","published":"2026-07-21T20:36:58Z","modified":"2026-09-17T18:57:27Z","cvss":[{"version":"4.0","score":7.7,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:N/SC:H/SI:N/SA:N","level":"high"}],"updated_at":"2026-11-02T17:28:10.38936Z"}],"ghsa":[{"id":"GHSA-rqhf-rg9p-w5gg","title":"lmdeploy's OpenAI-compatible API server contains a server-side request forgery vulnerability that...","description":"lmdeploy's OpenAI-compatible API server contains a server-side request forgery vulnerability that allows unauthenticated attackers to access internal services and cloud metadata endpoints by supplying a crafted image_url that redirects to internal targets. Attackers can send a POST request to the chat completions endpoint with an image_url pointing to an attacker-controlled server that responds with an HTTP 302 redirect to internal addresses such as loopback or instance-metadata endpoints, bypassing the initial URL safety check because redirects are followed without re-validating each hop through the safety guard.","status":"published","published":"2026-07-21T21:32:42Z","modified":"2026-07-23T18:30:57Z","cvss":[{"version":"4.0","score":9.2,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:H/VA:L/SC:N/SI:H/SA:L/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X","level":"critical"},{"version":"3.1","score":9.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N","level":"critical"}],"cwes":["CWE-918"],"updated_at":"2026-11-02T15:09:43.143268Z"}],"nvd":[{"id":"CVE-2026-63764","description":"LMDeploy through 0.14.0, fixed in commit 03c3130, contains a server-side request forgery (SSRF) vulnerability in the _load_http_url function within the connection.py media handler, where the private-IP guard validates only the original URL without re-validating hosts after HTTP redirects. An unauthenticated attacker can submit a crafted image_url to the chat completions endpoint pointing to an attacker-controlled host that returns a redirect to a private IP or cloud-metadata endpoint, causing the server to follow the redirect and expose internal service content through the model pipeline.","status":"published","published":"2026-07-21T21:16:53.35Z","modified":"2026-10-24T19:10:00.127Z","cvss":[{"version":"4.0","score":7.7,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:N/SC:H/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X","level":"high","assessor":"secondary"},{"version":"3.1","score":8.6,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N","level":"high","assessor":"secondary"}],"cwes":["CWE-918"],"updated_at":"2026-11-02T14:12:31.394335Z"}],"osv":[{"id":"CVE-2026-63764","title":"LMDeploy Server-Side Request Forgery via HTTP Redirect Bypass","description":"LMDeploy through 0.14.0, fixed in commit 03c3130, contains a server-side request forgery (SSRF) vulnerability in the _load_http_url function within the connection.py media handler, where the private-IP guard validates only the original URL without re-validating hosts after HTTP redirects. An unauthenticated attacker can submit a crafted image_url to the chat completions endpoint pointing to an attacker-controlled host that returns a redirect to a private IP or cloud-metadata endpoint, causing the server to follow the redirect and expose internal service content through the model pipeline.","status":"published","published":"2026-07-21T20:36:58.372Z","modified":"2026-10-28T02:31:09.692084012Z","cvss":[{"version":"4.0","score":7.7,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:N/SC:H/SI:N/SA:N","level":"high"}],"cwes":["CWE-918"],"updated_at":"2026-11-02T15:45:13.306117Z"}]}}