LMDeploy - Server-Side Request Forgery

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 the vision-language module. The loadimage function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating internal or...

Learning-to-Detect

Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models Official implementation of “Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models.” This repository contains the data-processing, hidden-state extraction, classifier training, safety-pattern...

Exploiting Vulnerabilities: Universal Adversarial Attacks on Vision-Language-Action Models in Robotics

Recently, Vision-Language-Action VLA models have revolutionized robotic manipulation by seamlessly integrating visual perception, language understanding, and action generation in an end-to-end learning framework. However, since these models are designed to interact directly with the physical worl...

CVE-2026-33626-Lab

CVE-2026-33626 — LMDeploy 비전-언어 SSRF 실습 환경 개요 이 저장소는 LMDeploy의 비전-언어 이미지 로딩 경로에서 발생하는 SSRFServer-Side Request Forgery, 서버 측 요청 위조 취약점인 CVE-2026-33626 을 재현합니다. 취약한 동작은 LMDeploy가 이미지 URL을 수신하고 서버 측 이미지 로더가 내부internal, 사설private, 루프백loopback, 링크-로컬link-local 주소를 제대로 차단하지 않은 채 해당 URL을 가져올 때 발생합니다. 이 ...

PYSEC-2026-2607 LMDeploy has Server-Side Request Forgery (SSRF) via Vision-Language Image Loading

Summary A Server-Side Request Forgery SSRF vulnerability exists in LMDeploy's vision-language module. The loadimage function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, an...

LMDeploy has Server-Side Request Forgery (SSRF) via Vision-Language Image Loading

SummaryA Server-Side Request Forgery SSRF vulnerability exists in LMDeploy's vision-language module. The loadimage 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...

PT-2026-59261

Summary A Server-Side Request Forgery SSRF vulnerability exists 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, a...

RedEdit: Agentic Red-Teaming of Image Safety Classifiers Via MCTS-Guided Photo-Editing

Image safety classifiers serve as a critical component of contemporary content moderation systems on the internet. However, their resilience against user-style malicious image editing remains underexplored. Such behaviors are highly prevalent in daily scenarios but difficult to fully reproduce. T...

MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents Via User-Generated Content

Mobile graphical user interface GUI agents driven by vision-language models VLMs perceive the screen as rendered pixels and choose actions from what they see, so they cannot reliably separate trusted interface elements from user-generated content. We present MIRAGE Mobile Injection of Realistic...

Exploit for Server-Side Request Forgery in Internlm Lmdeploy

CVE-2026-33626 — LMDeploy Vision-Language SSRF Lab Overvie...

STARE: Step-Wise Temporal Alignment and Red-Teaming Engine for Multi-Modal Toxicity Attack

Red-teaming Vision-Language Models is essential for identifying vulnerabilities where adversarial image-text inputs trigger toxic outputs. Existing approaches treat image generation as a black box, returning only terminal toxicity scores and leaving open the question of when and how toxic semanti...

LMDeploy CVE-2026-33626 Flaw Exploited Within 13 Hours of Disclosure

A high-severity security flaw in LMDeploy, an open-source toolkit for compressing, deploying, and serving large language models LLMs, has come under active exploitation in the wild less than 13 hours after its public disclosure. The vulnerability, tracked as CVE-2026-33626 CVSS score: 7.5, relate...

CVE-2026-33626

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 loadimage function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating...

VulnCheck KEV: CVE-2026-33626

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 loadimage function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating...

Server-side Request Forgery (SSRF)

Overview Affected versions of this package are vulnerable to Server-side Request Forgery SSRF via the loadimage and encodeimagebase64 functions in LMDeploy's vision-language module, which fetch URLs without validating whether the destination is an internal or private address. An attacker can acce...

LMDeploy has Server-Side Request Forgery (SSRF) via Vision-Language Image Loading

Summary A Server-Side Request Forgery SSRF vulnerability exists in LMDeploy's vision-language module. The loadimage function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, an...

EUVD-2026-23970

LMDeploy has Server-Side Request Forgery SSRF via Vision-Language Image Loading...

GHSA-6W67-HWM5-92MQ LMDeploy has Server-Side Request Forgery (SSRF) via Vision-Language Image Loading

Summary A Server-Side Request Forgery SSRF vulnerability exists in LMDeploy's vision-language module. The loadimage function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, an...

CVE-2026-33626

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 loadimage function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating...

CVE-2026-33626

LMDeploy SSRF in the vision-language module (prior to 0.12.3) allows an attacker to fetch arbitrary URLs via load_image() in lmdeploy/vl/utils.py without internal IP validation, potentially reaching cloud metadata services and internal networks. The issue also affects encode_image_base64() and ca...