Skip to main content

Lmdeploy

4 CVEs product

Monthly

CVE-2026-63764 HIGH PATCH This Week

Server-side request forgery in InternLM lmdeploy's OpenAI-compatible vision API server lets unauthenticated remote attackers coerce the server into fetching internal-only resources by abusing the image_url media-fetch path. Because the URL safety check validates only the initial URL and does not re-validate targets after an HTTP 302 redirect, an attacker-hosted endpoint can redirect the fetch to loopback services or cloud instance-metadata endpoints, exposing internal services and potentially cloud credentials. No public exploit is identified at time of analysis, EPSS is low (0.28%), and a vendor fix adding a media-domain allowlist is available.

SSRF Lmdeploy
NVD GitHub
CVSS 4.0
7.7
EPSS
0.3%
CVE-2026-33626 PyPI HIGH POC PATCH NEWS GHSA This Week

Server-Side Request Forgery (SSRF) in InternLM LMDeploy's vision-language module allows remote unauthenticated attackers to access cloud metadata services, internal networks, and sensitive resources through unvalidated URL fetching in the load_image() function. Affects all versions prior to 0.12.3. EPSS score not available; no public exploit identified at time of analysis. Patch released in version 0.12.3.

SSRF Lmdeploy
NVD GitHub VulDB
CVSS 3.1
7.5
EPSS
0.0%
CVE-2025-3163 PyPI MEDIUM POC This Month

A vulnerability was found in InternLM LMDeploy up to 0.7.1. Rated medium severity (CVSS 4.8), this vulnerability is low attack complexity. Public exploit code available and no vendor patch available.

Information Disclosure Lmdeploy
NVD GitHub VulDB
CVSS 4.0
4.8
EPSS
0.1%
CVE-2025-3162 PyPI MEDIUM POC This Month

A vulnerability was found in InternLM LMDeploy up to 0.7.1. Rated medium severity (CVSS 4.8), this vulnerability is low attack complexity. Public exploit code available and no vendor patch available.

Deserialization Lmdeploy
NVD GitHub VulDB
CVSS 4.0
4.8
EPSS
0.1%
EPSS 0% CVSS 7.7
HIGH PATCH This Week

Server-side request forgery in InternLM lmdeploy's OpenAI-compatible vision API server lets unauthenticated remote attackers coerce the server into fetching internal-only resources by abusing the image_url media-fetch path. Because the URL safety check validates only the initial URL and does not re-validate targets after an HTTP 302 redirect, an attacker-hosted endpoint can redirect the fetch to loopback services or cloud instance-metadata endpoints, exposing internal services and potentially cloud credentials. No public exploit is identified at time of analysis, EPSS is low (0.28%), and a vendor fix adding a media-domain allowlist is available.

SSRF Lmdeploy
NVD GitHub
EPSS 0% CVSS 7.5
HIGH POC PATCH This Week

Server-Side Request Forgery (SSRF) in InternLM LMDeploy's vision-language module allows remote unauthenticated attackers to access cloud metadata services, internal networks, and sensitive resources through unvalidated URL fetching in the load_image() function. Affects all versions prior to 0.12.3. EPSS score not available; no public exploit identified at time of analysis. Patch released in version 0.12.3.

SSRF Lmdeploy
NVD GitHub VulDB
EPSS 0% CVSS 4.8
MEDIUM POC This Month

A vulnerability was found in InternLM LMDeploy up to 0.7.1. Rated medium severity (CVSS 4.8), this vulnerability is low attack complexity. Public exploit code available and no vendor patch available.

Information Disclosure Lmdeploy
NVD GitHub VulDB
EPSS 0% CVSS 4.8
MEDIUM POC This Month

A vulnerability was found in InternLM LMDeploy up to 0.7.1. Rated medium severity (CVSS 4.8), this vulnerability is low attack complexity. Public exploit code available and no vendor patch available.

Deserialization Lmdeploy
NVD GitHub VulDB

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy