572 matches found
Poisoned Playbooks: Demystifying Knowledge Poisoning Effects on AI Security Agents
AI security agents increasingly rely on Retrieval-Augmented Generation RAG to use external security knowledge for vulnerability analysis and exploit reasoning. This creates a new risk: poisoned write-ups can be operationalized into incorrect exploit behavior. Yet, prior work on RAG poisoning has...
re
⚡ REVERSE ENGINEERING & BINARY EXPLOITATION ⚡ Welcome to my p...
Malicious Package
Overview ect-472839-ctf is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and this package...
rspwner
RSPWNER RSPWNER is a Rust-based AI-assisted CTF pwn assistant...
PHANTOM_CTF_HACKINGCLUB_BY_BSIDESRECIFE
Phantom — CTF Writeup & Exploit HackingClub / BSides Recife...
Kernel-Exploit-Dojo-255
Kernel-Exploit-Dojo-255 CTF kernel exploitation notes, PoCs,...
Kernel-Exploit-Dojo-962
Kernel-Exploit-Dojo-962 CTF kernel exploitation notes, PoCs,...
cybersec-mcp
🛡️ Cybersecurity Professor MCP Server Prof. Null — Tu pro...
-GodSearch
GodSearch v20.0 — THE SOVEREIGN 💀 Universal Exploit Sear...
human-connection-ctf
Human Connection Challenge: CTF Writeup Platform: Immersi...
autopenx
AutoPenX – A fully automated CTF-solving & penetration testing...
Malicious code in ctf-flare (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 23293f1bc28e465f7ffaf916fd8a6cc3958b873a2b338b81c0bf71bb146d1d36 package.json declares a postinstall script that runs node src/install.js after building a local binary. src/install.js is a 175 KB single-line payloa...
MAL-2026-3836 Malicious code in ctf-flare (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 23293f1bc28e465f7ffaf916fd8a6cc3958b873a2b338b81c0bf71bb146d1d36 package.json declares a postinstall script that runs node src/install.js after building a local binary. src/install.js is a 175 KB single-line payloa...
Exploit for SQL Injection in Cmsmadesimple Cms_Made_Simple
SimpleCTF-THM-Relatory First CTF successfully completed! This...
Malicious code in 0ctf-chalweb (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 6d7a129ab6079febb92ceac3587af97653477bce8a65b8e85bfa5bcae0293b0d The package's entire content xss.js is a 2-line cookie-stealing payload that creates an Image element pointing to...
CTFusion: A CTF-Based Benchmark for LLM Agent Evaluation
Recent advances in Large Language Models LLMs have enabled agentic systems for complex, multi-step tasks; cybersecurity is emerging as a prominent application. To evaluate such agents, researchers widely adopt Capture The Flag CTF benchmarks. However, current CTF benchmarks reuse existing...
When prompts become shells: RCE vulnerabilities in AI agent frameworks
In this article 1. A representative case study: Semantic Kernel 2. CVE-2026-26030: In-Memory Vector Store 3. CVE-2026-25592: Arbitrary file write through SessionsPythonPlugin 4. The vulnerability 5. Attack chain overview 6. Defending the agentic edge 7. Not bugs, but developed by design 8. CTF...
obliteratus-brain
OBLITERATUS BRAIN The Persistent Knowledge Layer for OBLITE...