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...

security-audit-skill

security-audit A coding-agent skill that turns your agent into a security auditor. It orchestrates multiple parallel agents through a six-phase pipeline -- recon, hunting, validation, reporting, structured output, and independent verification -- to find exploitable vulnerabilities with real impac...

reverse-skill

reverse-skill Cybersecurity Skills Router · 逆向技能路由包 Navigate the dark waters, sail against the stream. About · Getting Started · Usage · Routing · AI Bootstrap · Contributing 🌐 中文 About If you are an AI Agent, jump toREADMEAI.md and follow the instructions strictly. When an AI agent Claude Code,...

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...

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...

agentseal

Security toolkit for AI agents. Red-team prompts, detect MCP poisoning, scan skill files, trace toxic data flows. 225+ tests across 28 agents. Docs · MCP Registry · Dashboard · Blog Quick Start pip install agentseal or: npm install agentseal agentseal guard scan your machine - no API key needed...

skill-scanner

Skill Scanner A best-effort security scanner for AI Agent Skills that detects prompt injection, data exfiltration, and malicious code patterns. It combines pattern-based detection YAML + YARA-X, AST and dataflow analysis , an optional LLM-as-a-judge , and a bounded CEL decision layer over typed...

alexafaraday

https://www.faradaysec.com https://github.com/infobyte/faraday Amazon Alexa Faraday Skill Using Flask-ASK and VMware REST API's This is the GitHub Repository for Amazon Echo, Python Flask/Flask-ASK, and Faraday API's blogpost and subsequent updates. We leverage Flask-Ask to interact with the Amaz...

watermarks-remover

| | | || | | |/ |/| || |/ |/ |/ | |/| | | | | | |/ ||| | | | | | \ | | | | | \ | \ | \ | | | || / | | \ watermarks-remover Agent skill + stdlib Python service to strip multi-vendor AI provenance marks from text and files — for privacy and hygiene on content you own. The skill is a thin client:...

VibeSec-Skill

VibeSec-Skill Stop vibe coding vulnerabilities into production. An AI skill that brings 5+ years of bug bounty hunting experience directly into your AI coding workflow - so LLM models write secure code from the start. Introduction Vibe coding is fun until your app ends up on social media for all...

bug-reaper

BugReaper Structured web2 bug bounty AI skill — 18 vulnerability classes, 4 bug bounty platforms, zero AI slop. Compatible with OpenClaw, Cursor, Claude Code, Antigravity, and Windsurf. BugReaper is an Agent Skill that turns any compatible AI agent into a disciplined web2 bug bounty hunter. It...

CVE-2026-111717

The Arkon software, through version 0.9.2 , is vulnerable to a missing authorization flaw in the list_skill_versions function. The root cause is a failure to properly enforce the can_access_skill check, allowing authenticated employees with the default skill:read permission to bypass intended res...

CVE-2026-111717 Arkon through 0.9.2 Missing Authorization via Skills Versions API

Arkon through 0.9.2 contains a missing authorization vulnerability in listskillversions that allows authenticated employees to read other departments' skill version metadata by bypassing the canaccessskill check. Attackers holding the default skill:read permission can request GET...

geo-sleuth

🧭 geo-sleuth An agent skill that finds where a photo was taken — and shows its work. Works with …and any other agent that reads SKILL.md and runs shell commands. !From one photo to a camera position: the photo, the region scan, the skyline overlays, the evidence...

PT-2026-116116

Arkon through 0.9.2 contains a missing authorization vulnerability in list skill versions that allows authenticated employees to read other departments' skill version metadata by bypassing the can access skill check. Attackers holding the default skill:read permission can request GET...

CVE-2026-105032

The EnergizeLab Eilik and EilikO AI skill upload endpoint, served by the FastAPI AI inference and profiling services, does not require authentication and does not constrain uploaded file paths. An unauthenticated remote attacker can use path traversal to write arbitrary files, and thereby tamper...

CVE-2026-105032

The EnergizeLab Eilik and EilikO robots are vulnerable to an unauthenticated path traversal flaw within the FastAPI AI inference and profiling services . The AI skill upload endpoint fails to require authentication and does not constrain uploaded file paths, allowing a remote attacker to write ar...

CVE-2026-105032 EnergizeLab Eilik AI Skill Upload Unauthenticated Path Traversal Arbitrary File Write

The EnergizeLab Eilik and EilikO AI skill upload endpoint, served by the FastAPI AI inference and profiling services, does not require authentication and does not constrain uploaded file paths. An unauthenticated remote attacker can use path traversal to write arbitrary files, and thereby tamper...

cve-scanner

CVE Scanner for OpenClaw Version: 1.0.0 Author: Simon Autonomous Chief of Staff License: MIT Published: March 22, 2026 Category: Security, Tooling TL;DR Zero-dependency CVE scanner for OpenClaw. Checks your version against 522+ known vulnerabilities, recommends updates, displays recent...

agent

Binary Refinery Skill This repository stores a Claude skill for Binary Refinery. It can augment your malware analysis agent with a number of useful tools for data extraction and transformation. !CAUTION Make sure you are using refinery version 0.10.5 or later. The skill relies on changes to the...