エージェント向けプロンプト・インジェクション防御チェックリスト
Perform comprehensive website health checks covering performance, broken links, security headers, accessibility, and SEO issues.
Systematically identifies, scores, and prioritizes technical debt across codebases with impact analysis and detailed remediation roadmaps for engineering teams.
Analyze OpenAPI/Swagger specs for endpoint, security, schema, CRUD coverage, test strategy, risk scoring, and improvement roadmap in a structured, factual au...
Scan websites and content to identify SEO gaps, analyze meta tags, technical factors, keyword use, and provide competitor comparison insights.
审计本地 openclaw 的安全配置与运行暴露面。用于检查、验证、解释和总结当前机器或沙箱中的 openclaw 相关安全设置，包括代理配置、sandbox 配置、docker 端口暴露、gateway 检查、文件权限、workspace symlink 风险、本地监听端口以及整体本地安全状态。
Evaluates business workflows across 8 areas to identify automation opportunities, estimate time and cost savings, and prioritize processes by ROI for digital...
Analyze multi-cloud spend data to identify waste, rightsizing, reserved instance savings, and generate a prioritized 90-day cost optimization roadmap.
对 OpenClaw 部署进行只读安全审计，检测环境泄露、认证配置、恶意 Skill 等已知风险和漏洞。
Network scanning MCP server wrapping nmap. Provides 14 purpose-built tools for host discovery, port scanning (SYN/TCP/UDP), service & OS detection, NSE scrip...
Identifies burning and decaying Meta Ads by running the eonik Budget heuristics engine.
提供基于链上数据和项目多维分析的加密项目安全审计及风险评分，助力投资风险识别和决策。
Scans installed or remote OpenClaw skills for security risks like credential leaks and suspicious code to prevent supply chain attacks.
Five-layer security for AI agents — prompt injection defense, secret protection, PII scanning
This skill should be used when the user asks to "audit content quality", "EEAT score", "E-E-A-T audit", "content quality check", "CORE-EEAT audit", "helpful...
--- name: medical_revenue_audit description: Audits hospital surgical logs against billing to find revenue leakage. --- # Medical Revenue Audit Skill When asked to perform a medical audit: 1. **Identi
This skill should be used when the user asks to "audit domain authority", "domain trust score", "CITE audit", "how authoritative is my site", "domain credibi...
Three-tier code quality defense: L1 quick scan, L2 deep audit (via bug-audit), L3 cross-validation with adversarial testing. 三级代码质量防线。
Perform comprehensive security audits on skills to identify vulnerabilities, unsafe patterns, and compliance issues. Use when auditing skills for security, c...
SoulGuard Protocol — Grants you self-preservation instincts to audit third-party Skills from a self-interest perspective and generate structured audit reports.
Security audit and vulnerability scanner for AI agent skills before installation. Use when: (1) evaluating a skill from an untrusted source, (2) auditing a s...
Audit any website across 8 quality signals to determine if it is outdated, broken, or neglected. Returns a structured audit dict used by the lead-scorer skill.
Pinboard bookmark management — tag audit, dead link detection, and timeliness check. Triggers on "pinboard", "bookmark", "tag audit", "dead link", "timelines...