bug-reaper

BugReaper 구조화된 web2 버그 바운티 AI 스킬 — 18가지 취약점 클래스, 4개 버그 바운티 플랫폼, AI 노이즈 제로. OpenClaw, Cursor, Claude Code, Antigravity, Windsurf와 호환 가능. BugReaper는 Agent Skill로, 호환되는 AI 에이전트를 훈련된 web2 버그 바운티 헌터로 바꿔줍니다. 증거 기반 검증을 강제하고, HackerOne, Bugcrowd, Intigriti, YesWeHack의 실제 트라이지 과정을 시뮬레이션하며, 낮은 심각도의 버그를 연결하...

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...

watermarks-remover

| | | || | | |/ |/| || |/ |/ |/ | |/| | | | | | |/ ||| | | | | | \ | | | | | \ | \ | \ | | | || / | | \ watermarks-remover エージェントスキル + 標準ライブラリのみの Python サービスで、テキストおよびファイルから複数ベンダーの AI 由来マーク を除去します — あなたが所有する コンテンツのプライバシーと衛生のために。このスキルはシンクライアントです。HTTP 経由で機構を操作するため、エージェントホストに Python は不要です。 レイヤー| 対象|...

x86-cpp-reversing-skill

x86-cpp-reversing C++ からコンパイルされた 32 ビットリトルエンディアン x86 IA-32 バイナリおよび逆アセンブリをリバースエンジニアリングするための Claude Code スキル。ELF または PE バイナリからクラスレイアウト、vtable、仮想ディスパッチ、RTTI/継承階層を復元し、その構造を把握した後に発生するワークフロー -- カスタムファイルフォーマットの復元、データファイルのインデックス付きエントリをそれを使用するコード/エンティティにマッピングすること、そしてその過程で難読化やアンチデバッグのトリックを認識すること -- をカバーします...

exploitBenchSkill

OpenSec ExploitBench V8 PoC Skill An installable Pi and Agent...

SecureAI-Scan v0.8.0

SecureAI-Scan The AI security scanner that proves its findings. SecureAI-Scan finds LLM, MCP, Agent Skill, and RAG vulnerabilities in TypeScript, JavaScript, and Python — and shows you the evidence: the exact source → flow → sink path for every dataflow finding, resolved through real imports, not...

SecureAI-Scan v0.5.0

SecureAI-Scan The AI security scanner that proves its findings. SecureAI-Scan finds LLM, MCP, Agent Skill, and RAG vulnerabilities in TypeScript, JavaScript, and Python — and shows you the evidence: the exact source → flow → sink path for every dataflow finding, resolved through real imports, not...

Fake AI Agent Skill Passed Security Scans and Reportedly Reached 26,000 Agents

Security firm AIR built a fake AI agent skill, pushed it through a popular skill marketplace and an Instagram ad, and says it reached roughly 26,000 agents, including some on corporate accounts. Every skill security scanner the firm tested it against marked it safe. The payload was harmless by...

CVE-2026-48116 AnythingLLM: RCE via ripgrep --pre argument injection in filesystem-search-files agent skill

AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. Prior to 1.13.0, the filesystem-search-files agent skill passes its LLM-controlled pattern parameter to ripgrep as a positional argument without a -- end-of-options separato...