bug-bounty
AI-powered bug bounty hunting from your terminal - recon, 20 vuln classes, autonomous hunting, and report generation. All inside Claude Code.
2,832 个安全任务的工具和技能
AI-powered bug bounty hunting from your terminal - recon, 20 vuln classes, autonomous hunting, and report generation. All inside Claude Code.
Multi-agent novel production system — AI agents autonomously write, audit, and revise novels with human review gates
This skill helps Claude write secure code and prevent common vulnerabilities.
|
Security audit tool for third-party AI API relay/proxy services. Detects hidden prompt injection, prompt leakage, instruction override, and context truncation.
微信小程序全自动安全审计 Skill，基于 Claude Code Agent Teams。7 Agent 协作，覆盖敏感信息、API接口、加密分析、漏洞分析四大维度。采用脚本+LLM双层架构，脚本保证覆盖率，LLM保证准确率。
A Claude Code skill that scans Solidity codebases for security vulnerabilities by referencing 36 unique vulnerability types
RLM based security scanner for massive .NET codebases
OpenClaw operations skill with health checks, repair scripts, watchdogs, update triage, and security scans.
Claude skill to run code audits
CLI tool for managing iKuai routers — network, VPN, firewall, users, QoS and more from the terminal. AI-agent ready.
Comprehensive Java code health analyzer that scans for security, performance, correctness, and architecture issues. Outputs a 0-100 score with actionable diagnostics.
Analyze a DeFi protocol's risk profile across smart contract, off-chain, and track-record dimensions. Use when the user wants a risk analysis of a DeFi project, to check protocol security, or to assess risk. Trigger words include "risk analysis", "analyze protocol", "audit defi", "check security", "defi risk", "protocol vulnerability", "is it safe".
"Multi-scanner security gate. TRIGGER when: user mentions installing, adding, or reviewing a skill to Claude Code, OpenClaw, or any other AI agent. Detects malicious code, vulnerabilities, and suspicious patterns."
470 security tests for AI agent systems — MCP, A2A, x402/L402, decision governance, benchmark integrity, skill supply chain. AIUC-1 pre-cert, NIST AI 800-2 aligned, CVE-2026-25253 reproduction. v4.4.2
Claude Code安全扫描Skill：说句中文就能扫漏洞，基于Semgrep | Security scanning skill for Claude Code, powered by Semgrep
The definitive SEO + GEO skill for Claude. Full site audits with scored findings, AI search optimization (Google AI Overviews, ChatGPT, Perplexity), schema generation, E-E-A-T assessment, and 20 diagnostic scripts. Three modes: Audit → Plan → Execute.
Security check skill. Triggers on "Could you please run a security check?", "セキュリティチェックをお願いします。", "请帮我做一次安全检查。". セキュリティチェックのデモスキル。「セキュリティチェックをお願いします。」「请帮我做一次安全检查。」などのリクエストで発動する。
一个专业的 java代码审计 Skill
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
A security-first plugin that places a "Human-in-the-Loop" gatekeeper between the AI and high-risk actions.
🐝 Scoping Bee - AI-powered pre-audit scoping skill for Solidity & Solana smart contract security engagements
Control the information flow between autonomous agents. PII redaction, on-chain payment verification, and audit trails. Open source.
Collective AI memory. Sovereign. Local-first. Searchable. Encrypted worldwide sync.
Claude skill for SaaS security auditing — 16 domains, 95 checks, OWASP-based
Skill Vetter - Security-first skill vetting for AI agents
Forge battle-tested CLAUDE.md files that actually get followed. Audit, score, and generate CLAUDE.md with anti-slop rules, plan enforcement, and verification gates.
Security-first skill vetting for AI agents
一个调用nano banana的skill，通过 Google 账号登录态而非 API key，自带提示词优化/A skill for gemini and nano banana editing with Google account authentication. Built-in prompt optimization /
OpenClaw 安全巡检工具，一键执行系统安全扫描并生成通俗易懂的报告。 使用场景：用户说"安全巡检"、"安全检查"、"安全审计"、"巡检"、"security audit"、"检查安全"、"系统安全"等。 触发条件：任何与 OpenClaw 安全检测、审计、巡检相关的请求。
Use this skill whenever the user asks you to review, critique, audit, score, or improve a UI, frontend component, layout, or design mockup. Also trigger if they ask about UX best practices, user experience, cognitive load, accessibility, or whether a design is user-friendly. This skill provides a rigorous framework for evaluating UI code and designs against 25+ established psychological principles, WCAG 2.2 accessibility criteria, and Nielsen's 10 usability heuristics, with a quantitative scoring rubric and platform-aware guidance.
Toolkit completo para detectar, analizar y remediar malware PHP en servidores Linux de web hosting (CWP/cPanel) con WordPress. Incluye auditoría forense, hardening post-compromiso y generación de reportes HTML ejecutivos.
Claude Code skill that deploys any web app, API, or agent to the internet — strict pre-deploy audit, preview → prod flow. Bilingual EN/ES. By @soyenriquerocha · Tododeia.
雙 AI 全倉庫 bug audit Skill for Claude Code
Skill security scanner for Clawhub
AI agent skill for Solidity smart contract security auditing
448 attack personas. 24 squads. 9 phases. Adversarial security audit framework for Claude Code.
Sanitized Terraform/Ansible template for a private AI-agent workbench around Hermes Agent on a hardened Hetzner VPS.
🦸 AI skill that turns any LLM into a Splunk expert — architecture, SPL, development, administration, ES, SOAR, and more
Claude Code Skill to audit persistent approval-bypass settings in Claude Code and Codex
A Claude Code skill for AI consultants that conducts a structured 5-domain interview, auto-scores each domain 1–5, and generates a complete AI Readiness Audit Report with scorecard, findings, recommendations, effort/impact matrix, and 90-day roadmap.
|
Claude Code skill: brutally honest landing page audit — scored out of 100 across 6 dimensions with specific fixes in plain English
"Use this skill to audit, check, or evaluate the current workspace's AI configuration against best practices. This is the RIGHT tool whenever someone wants to know if their CLAUDE.md is good, if their workspace setup is correct, what configuration is missing, or whether the project follows AI tooling best practices. Covers Claude Code and GitHub Copilot config files. Produces a scored compliance report with findings and next steps. NOT for creating config files — only for reviewing what exists."
Security scanner for OpenClaw skills. Detects prompt injection, data exfiltration, and malicious code before installation.
Nightly librarian intelligence cycle: ingest last 24h of records, cluster patterns/failures, generate doctrine candidates, run hygiene audit, re-rank active doctrine, build next-day guidance packet, write scorecard, and queue promotion candidates.
A security posture assessment for [OpenClaw](https://github.com/openclaw/openclaw) based on ["Don't Let the Claw Grip Your Hand"](https://arxiv.org/abs/2603.10387) (Shan et al., 2026).
>
OpenClaw skill: audit and repair Linux/macOS hosts running OpenClaw
"Enterprise MCP Security Gateway with MCP-Only Sandbox Enforcement"