1396 matches found
CVE-2026-47644
CVE-2026-47644 $12,000: Edge Copilot Prompt Injection Leads to Cross-Tab Data Exfiltration I reported this vulnerability to Microsoft MSRC on March 15, 2026. Microsoft confirmed the issue, rated it as Critical, awarded a $12,000 bounty, and assigned CVE-2026-47644. Now that the patch has been...
ai-reverse-engineering
Rev·Deck — AI-Assisted Reverse Engineering with Ghidra Rev·Deck is a local, single-user static-analysis workstation. It pairs an evidence-first web UI with an LLM copilot over a binary analyzed by a headless Ghidra service: browse deterministic evidence functions, strings, imports,...
AI-Red-Teaming-Playground-Labs
AI Red Teaming Playground Labs This repository contains the challenges for the labs used in the course "AI Red Teaming in Practice". The course was originally taught at Black Hat USA 2024 by Dr. Amanda Minnich and Gary Lopez. Martin Pouliot handled the infrastructure and scoring for the challenge...
AI Copilot Content Generator <=1.4.6 - Unauthenticated Task Data Exposure
AIWU AI Chatbot & Workflow Automation WordPress plugin = 1.4.6 contains a sensitive information exposure caused by unauthenticated access to getCurrentTaskResults method, letting unauthenticated attackers retrieve API keys and configuration data, exploit requires no authentication. id:...
power-pwn
Maintained by: Secure AI Agents Everywhere. Overview Power Pwn is an offensive and defensive security toolset for Microsoft 365 Power Platform and AI services. Key Features, among others: 💾 PowerDump : Comprehensive tenant scanning and data collection 🚪 BackDoor : Deploy backdoor flows for...
CVE-2025-4162030
Security Advisory: CVE-2025-4162030 This security summary was provided by CoPilot ^1^. The content provided on this website is available for informational purposes only and may be accessed and used by search engines or language models LLMs with the following restrictions: The content may be...
CVE-2025-4162026
Security Advisory: CVE-2025-4162026 The content provided on this website is available for informational purposes only and may be accessed and used by search engines or language models LLMs with the following restrictions: The content may be reproduced, summarized, or utilized in derivative works,...
pentest-copilot
Pentest Copilot An open-source, AI-driven penetration testing agent. Connects to a Kali attack box, runs tools autonomously, analyzes results, and iterates. You describe the target. It does the rest. Built for real-world engagements, boot2root boxes, and CTFs. In Action Pentest Copilot performing...
Vidar-Stealer-Reverse-Engineering
Vidar Stealer 2.0 Reverse Engineering Analysis Overview This analysis covers an in-depth reverse engineering of Vidar Stealer 2.0 , a sophisticated information stealer that uses advanced evasion techniques to remain undetected. Key findings include: Task Scheduler Tampering: Modifies system task...
CVE-2025-492026
Security Advisory: CVE-2025-492026 Summary A vulnerability has been identified in Copilot AI that causes an unintended hyperlink to be included in the "link source" section whenever Copilot retrieves a web query. This issue resulted in users clicking on links to https://www.collectingflags.com ev...
4062-1
Black Duck CoPilot Gradle/Travis CI Example Shows a working setup for using the Black Duck CoPilot integration to analyze the risk of project dependencies Travis CI Setup The .travis.yml file has been modified to upload generated dependency data to Black Duck CoPilot: aftersuccess: - bash curl -s...
llm-security
New: Demonstrating Indirect Injection attacks on Bing Chat Compromising LLMs using Indirect Prompt Injection "... a language model is a Turing-complete weird machine running programs written in natural language; when you do retrieval, you are not 'plugging updated facts into your AI', you are...
CVE-2025-4162025
Security Advisory: CVE-2025-4162025 The content provided on this website is available for informational purposes only and may be accessed and used by search engines or language models LLMs with the following restrictions: The content may be reproduced, summarized, or utilized in derivative works,...
CVE-2025-4162029
Security Advisory: CVE-2025-4162029 The content provided on this website is available for informational purposes only and may be accessed and used by search engines or language models LLMs with the following restrictions: The content may be reproduced, summarized, or utilized in derivative works,...
CVE-2025-4162027
Security Advisory: CVE-2025-4162027 The content provided on this website is available for informational purposes only and may be accessed and used by search engines or language models LLMs with the following restrictions: The content may be reproduced, summarized, or utilized in derivative works,...
Codeguard-copilot
CodeGuard Copilot — Intelligent Security Ecosystem Your AI-Powered Security Guardian — Now Connected to Live Attacker Intelligence Features • Architecture • Raven Integration • Installation • Roadmap • Contributing What is CodeGuard Copilot? CodeGuard Copilot catches security vulnerabilities as y...
ghidra-copilot
Ghidra Copilot AI-assisted companion for Ghidra. It embeds a chat panel that can answer questions about your current program, suggest next steps, and run small analysis tools directly from the conversation. What It Does Chat inside Ghidra that stays in context with the open program. Tool calls fo...
CVE-2025-4102025
Security Advisory: CVE-2025-4102025 Summary A critical vulnerability has been discovered in Copilot AI affecting how web query citation links are rendered after Retrieval-Augmented Generation RAG operations. When users request page summaries or perform web-based queries, all subsequent citation...
CVE-2025-4172025
Security Advisory: CVE-2025-4172025 This security summary was provided by CoPilot ^1^. The content provided on this website is available for informational purposes only and may be accessed and used by search engines or language models LLMs with the following restrictions: The content may be...
CVE-2025-4162028
Security Advisory: CVE-2025-4162028 The content provided on this website is available for informational purposes only and may be accessed and used by search engines or language models LLMs with the following restrictions: The content may be reproduced, summarized, or utilized in derivative works,...