ai-captcha-bypass

Solucionador de CAPTCHA impulsado por IA Este proyecto es una herramienta de línea de comandos basada en Python que utiliza grandes modelos multimodales LMM como GPT-4o de OpenAI y Gemini de Google para resolver automáticamente varios tipos de CAPTCHA. Aprovecha Selenium para la automatización de...

Multimodal-Unlearnable-Examples

Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning ACM MM2024 Abstract : Multimodal contrastive learning MCL has shown remarkable advances in zero-shot classification by learning from millions of image-caption pairs crawled from the Internet. However, this...

bordair-multimodal

Multimodal Prompt Injection Dataset 516,588 个带标签样本 （251,782 个攻击样本 + 251,576 个良性样本，外加一个 13,230 样本的真实世界验证划分），涵盖五个数据集版本及外部数据集摄入，覆盖跨模态、多轮、对抗性后缀、越狱模板、间接注入、工具操纵、智能体、规避、推理 DoS、视频生成、VLA 机器人、LoRA 供应链、原生音频 LLM、RAG 优化、MCP 跨服务器、编码智能体、序列化边界以及智能体技能供应链等针对 AI 系统的攻击。攻击样本与良性样本按 1:1 平衡（审计清理后比率为 0.9992:1）。...

hcaptcha-challenger

hCaptcha Challenger 🚀 Afronta con elegancia el desafío de hCaptcha con un modelo de lenguaje grande multimodal. Introducción No depende de ningún script de Tampermonkey. No utiliza ningún servicio de terceros anti-captcha. Solo implementa algunas interfaces para hacer posible IA vs IA...

Multimodal-web-attack-Dataset

MWAD: Un conjunto de datos multimodal de ataques web para la detección de inyección SQL basada en IA Descripción general El conjunto de datos multimodal de ataques web MWAD es un novedoso conjunto de datos etiquetado de ciberseguridad desarrollado como parte de la investigación del autor en...

EXPLOIT-CVE-2026-22778

CVE-2026-22778 — RCE en vLLM en el procesamiento de vídeo Laboratorio vulnerable + prueba de concepto para CVE-2026-22778 CVSS 9.8, una cadena de ejecución remota de código no autenticada en la ruta de ingesta multimodal de vLLM...

safety-awareness

Transfer Safety Awareness para la Deriva de Seguridad entre Modalidades Implementación oficial de Transfer Safety Awareness for Cross-Modal Safety Drift in Multimodal Large Language Models EMNLP 2026 Findings. Este repositorio contiene el pipeline de dirección de conciencia de seguridad de...

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...

vLLM 0.8.3 - 0.14.0 - Information Disclosure

vLLM 0.8.3 to - 0.14.1 contains an information disclosure caused by leaking a heap address in error messages from the multimodal endpoint when processing invalid images, letting remote attackers reduce ASLR entropy, exploit requires sending invalid images. id: CVE-2026-22778 info: name: vLLM 0.8....

EUVD-2026-80070

A security flaw has been discovered in ag-ui-protocol ag-ui 0.3.0. Affected is the function urllib.request.urlopen of the file integrations/aws-strands/python/src/aguistrands/utils.py of the component Multimodal Content. The manipulation of the argument Value results in server-side request forger...

CVE-2026-92184

A security flaw has been discovered in ag-ui-protocol ag-ui 0.3.0. Affected is the function urllib.request.urlopen of the file integrations/aws-strands/python/src/aguistrands/utils.py of the component Multimodal Content. The manipulation of the argument Value results in server-side request forger...

CVE-2026-92184

A server-side request forgery (SSRF) vulnerability exists in ag-ui-protocol ag-ui 0.3.0 , affecting the function urllib.request.urlopen in the file integrations/aws-strands/python/src/ag_ui_strands/utils.py within the Multimodal Content component. Manipulation of the argument Value enables the fl...

CVE-2026-92184 ag-ui-protocol ag-ui Multimodal Content utils.py urllib.request.urlopen server-side request forgery

A security flaw has been discovered in ag-ui-protocol ag-ui 0.3.0. Affected is the function urllib.request.urlopen of the file integrations/aws-strands/python/src/aguistrands/utils.py of the component Multimodal Content. The manipulation of the argument Value results in server-side request forger...

CVE-2026-92184 ag-ui-protocol ag-ui Multimodal Content utils.py urllib.request.urlopen server-side request forgery

A security flaw has been discovered in ag-ui-protocol ag-ui 0.3.0. Affected is the function urllib.request.urlopen of the file integrations/aws-strands/python/src/aguistrands/utils.py of the component Multimodal Content. The manipulation of the argument Value results in server-side request forger...

ContextHound

ContextHound 静态分析工具，可扫描你的代码库以发现LLM提示注入和多模态安全漏洞。离线运行，无需API调用。 ContextHound 生态系统 ContextHound 可贯穿你的整个开发和浏览工作流： 工具| 功能| 安装方式 ---|---|--- CLI / npm 包| 扫描代码库中的提示注入漏洞。集成到 GitHub Actions，输出 SARIF、JSON、HTML 等格式。| npm install -g context-hound VS Code 扩展| 编码时内联显示发现结果、代码操作、输出通道、状态栏。| VS Code 市场 浏览器扩展| 在任何 A...

vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections

Summary vllm/transformersutils/processors/mimov2omni.py — the multimodal processor for MiMoV2OmniForCausalLM — issues requests.get... directly on user-supplied image and audio URL strings and Image.open... on user-supplied local paths, without the SSRF / allowedlocalmediapath checks that...

GHSA-4HHP-H66F-J5J7 vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections

Summary vllm/transformersutils/processors/mimov2omni.py — the multimodal processor for MiMoV2OmniForCausalLM — issues requests.get... directly on user-supplied image and audio URL strings and Image.open... on user-supplied local paths, without the SSRF / allowedlocalmediapath checks that...

CVE-2026-85686

ms-swift 4.5.2 contains a server-side request forgery vulnerability in the swift deploy OpenAI-compatible API that fetches multimodal media URLs without validation or redirect filtering. Unauthenticated attackers can supply arbitrary imageurl, audiourl, or videourl parameters to make the server...

CVE-2026-85686 ms-swift 4.5.2 Unauthenticated SSRF via Multimodal Media URLs

ms-swift 4.5.2 contains a server-side request forgery vulnerability in the swift deploy OpenAI-compatible API that fetches multimodal media URLs without validation or redirect filtering. Unauthenticated attackers can supply arbitrary imageurl, audiourl, or videourl parameters to make the server...

EUVD-2026-71135

ms-swift 4.5.2 contains a server-side request forgery vulnerability in the swift deploy OpenAI-compatible API that fetches multimodal media URLs without validation or redirect filtering. Unauthenticated attackers can supply arbitrary imageurl, audiourl, or videourl parameters to make the server...