CVE-2026-33626: fallo de gravedad alta en InternLM lmdeploy
LMDeploy Vulnerable to Server-Side Request Forgery (SSRF) via Vision-Language Image Loading
Publicada el · Actualizada el
78Vexday Risk Score
Corrige ahora. Ella explotación observada por VulnCheck y tiene exploit funcional público.
ssvc Actcvss 7.5epss 1.5%
de la publicación al arma23 días
Publicada en NVD20 abr
1ª PoC+23d
VulnCheck+2d
probabilidad de explotación
1.5%top 26% de las CVE
explotación observada
síVulnCheck
1 exploit(s) público(s)
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions prior to 0.12.3 have a Server-Side Request Forgery (SSRF) vulnerability in LMDeploy's vision-language module. The `load_image()` function in `lmdeploy/vl/utils.py` fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, and sensitive resources. Version 0.12.3 patches the issue.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Productos afectados
InternLM · lmdeployPoCs públicas encontradas — 1
githubgithub.com/rootdirective-sec/CVE-2026-33626-Lab★ 0⚠ Recursos públicos, para evaluar la exposición de sistemas que controlas o estás autorizado a probar. Prueba solo con autorización.
CVEs relacionadas — InternLM lmdeploy
En el mismo producto, de las más peligrosas a las menos.
CVE-2026-76850CRITICALLMDeploy Remote Code Execution via Unsafe Pickle Deserialization in the Disaggregated Serving Peer ConnectorEPSS 1.3%CVE-2025-59953CRITICALLMdeploy has Remote Code Execution by Pickle Deserialization via zmq_rpc.call_and_response() in InterLM/lmdeployEPSS 0.8%CVE-2026-92971HIGHInternLM LMDeploy through 0.17.0 Assertion Denial of ServiceEPSS 0.7%CVE-2025-66455CRITICALLMDeploy has Remote Code Execution by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.pyEPSS 0.7%CVE-2026-92983HIGHInternLM LMDeploy through 0.17.0 Memory Exhaustion via Session ID MismatchEPSS 0.7%CVE-2025-67729HIGHlmdeploy vulnerable to Arbitrary Code Execution via Insecure Deserialization in torch.load()EPSS 0.6%