Описание
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.
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.
Ссылки
- https://nvd.nist.gov/vuln/detail/CVE-2026-63764
- https://github.com/InternLM/lmdeploy/issues/4761
- https://github.com/InternLM/lmdeploy/pull/4734
- https://github.com/InternLM/lmdeploy/commit/03c313006d17cc3feae86b633c44206a997c44db
- https://github.com/InternLM/lmdeploy
- https://www.vulncheck.com/advisories/lmdeploy-server-side-request-forgery-via-http-redirect-bypass
- https://www.vulncheck.com/advisories/lmdeploy-server-side-request-forgery-via-http-redirect-bypass-of-private-ip-guard-in-vision-image-fetch
EPSS
9.2 Critical
CVSS4
9.3 Critical
CVSS3
CVE ID
Дефекты
Связанные уязвимости
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.
EPSS
9.2 Critical
CVSS4
9.3 Critical
CVSS3