pentest-ai-agents

pentest-ai-agents 50 Claude Code subagents for penetration testing. Quick Start | Cheatsheet | Coverage | Agents | Examples Table of Contents What's New in v3.3 What's New in v3.2 Agent Map What's New in v3.1 Quick Start Cheatsheet Coverage Agents Tier 1 vs Tier 2 Examples Running Tools in a...

ctf-skills

ctf-skills Agent Skills for solving CTF challenges — web exploitation, binary pwn, crypto, reverse engineering, forensics, OSINT, and more. Works with any tool that supports the Agent Skills spec, including Claude Code. Installation npx skills add ljagiello/ctf-skills Environment Setup Two setup...

nova-tracer

Nova-tracer Agent Monitoring and Visibility Security monitoring and prompt injection defense for Claude Code using the NOVA Framework. Features Session Tracking - Captures all tool usage with timestamps and metadata Prompt Injection Detection - Three-tier scanning keywords, semantic ML, LLM -...

system_prompts_leaks

System Prompts Leaks The full verbatim system prompts behind the most popular chatbots in the world. Carefully curated and complete. Feel free to open up a PR or get in contact if you got a different result. The Washington Post built its interactive story on prompts from this repo: See the hidden...

thrunt-god

From signal, to swarm. No gods. Only Thrunt. Threat hunting command system for agentic IDEs. Claude Code · OpenCode · Gemini · Codex · Copilot · Cursor · Windsurf /thrunt:autonomous | one command, full hunt Install · Phases · Commands · Flows · Artifacts Installation npx thrunt-god@latest --claud...

Boucle-framework

Boucle Claude Code hooks that actually enforce your rules. 7 standalone hooks, plus enforce-hooks for CLAUDE.md policy, audit tooling, 1,900+ tests, and a searchable Claude Code gaps corpus with severity ratings and workarounds. Quick links: Check your setup · Install hooks · Known limitations ·...

tengu

Tengu — Pentesting MCP Server "In Japanese mythology, the Tengu is a fierce mountain spirit — master strategist, warrior, and trainer of samurai. In cybersecurity, it guides you through every phase of the hunt." From recon to report — AI-assisted pentesting in one command. Tengu is an MCP server...

Claude-BugHunter

claude-bughunter A self-contained Claude skill bundle for bug hunting and external red-team work · 83 skills · 15 slash commands · 681 disclosed-report patterns 433 now individually cited & auditable across 24 core vulnerability classes · enterprise identity + infrastructure attack matrices ·...

skills

Trail of Bits Skills Marketplace Trail of Bits skills and plugins for AI-assisted security analysis, testing, and development. Install this marketplace in Claude Code or Codex, or import it into your ChatGPT workspace marketplace. Also see: claude-code-config · codex-config · skills-curated ·...

buyer-eval-skill

Buyer Eval An AI analyst for buying B2B software. Give it the vendors you're considering. Buyer Eval investigates what they claim, checks the evidence, finds the gaps and contradictions, and gives you the questions to ask before you buy. You get a Decision Brief you can forward to everyone else...

claude-code-guardrails

We have since built a dedicated product to help developers manage AI permissions better, which we intend to make open source. Check it out atstoplight.ai. Claude Code Guardrails settings.json works if: You're fine editing JSON and killing Claude Code sessions every time policy changes Your securi...

android-reverse-engineering-skill

Android Reverse Engineering & API Extraction — Claude Code skill A Claude Code skill that decompiles Android APK/XAPK/JAR/AAR files and extracts the HTTP APIs used by the app — Retrofit endpoints, OkHttp calls, hardcoded URLs, authentication patterns — so you can document and reproduce them witho...

lisa.py

LLDB MCP Integration This project provides a Model-Context Protocol MCP integration for LLDB, allowing AI assistants like Claude to interact with your debugging sessions through a standardized interface. Overview The integration consists of two main components: 1. server.py - An MCP server that...

CVE-2026-88968

A flaw was found in Claude Code. An attacker capable of executing code within the tool's sandbox can overwrite arbitrary files outside the designated workspace, leading to a sandbox escape. This issue occurs because the Edit tool verifies file paths without securing them against changes to the...

claude-code-backdoor

Claude Code Backdoor PoC A Proof of Concept demonstrating how Claude Code Anthropic's CLI AI agent hooks can be leveraged for Initial Access and Persistence. ⚠️ Disclaimer This project is for educational and ethical security testing purposes only. Unauthorized access to computer systems is illegal...

juice-shop

OWASP Juice Shop The most trustworthy online shop out there. @dschadow — The best juice shop on the whole internet! @shehackspurple — Actually the most bug-free vulnerable application in existence! @vanderaj — First you 😂😂then you 😢 @kramse — But this doesn't have anything to do with juice...

CVE-2026-88968

Claude Code is an agentic coding tool. Prior to 2.1.251, the Edit tool validates a target using pathname and symlink resolution that is not bound to the underlying directory inode or file descriptor. On macOS, attacker-controlled code running in the Bash sandbox can atomically replace an...

CVE-2026-88066

Claude Desktop is Anthropic's desktop application for interacting with Claude. Prior to 1.8089.0, Claude Desktop on Windows invokes git.exe through uvspawn without an absolute path, allowing Windows search-path resolution to select a malicious git.exe placed in the opened project's current workin...

EUVD-2026-116209

Claude Code is an agentic coding tool. Prior to 2.1.251, the Edit tool validates a target using pathname and symlink resolution that is not bound to the underlying directory inode or file descriptor. On macOS, attacker-controlled code running in the Bash sandbox can atomically replace an...

CVE-2026-88968 Claude Code: TOCTOU Race in Edit Tool Allows File Writes Outside the Workspace

Claude Code is an agentic coding tool. Prior to 2.1.251, the Edit tool validates a target using pathname and symlink resolution that is not bound to the underlying directory inode or file descriptor. On macOS, attacker-controlled code running in the Bash sandbox can atomically replace an...