Security

Self-improving agent framework with dharmic security

The only agent framework that improves itself while you sleep. Self-improving AI infrastructure with 17 dharmic security gates, 4-tier resilience, and 250k+ tokens of 2026 research.

Audit an iOS app repo (Swift/Xcode or React Native/Expo) for App Store compliance and release readiness; output a pass/warn/fail report and publish checklist.

Security advisory feed with automated NVD CVE polling for OpenClaw-related vulnerabilities. Updated daily.

Review and audit agent skills (SKILL.md files) for quality, correctness, and effectiveness. Use when evaluating a skill before publishing, reviewing someone else's skill, scoring skill quality, identifying defects in skill content, or improving an existing skill.

Audit ClawHub skills for security threats before installing them.

Masumi Network skill for warranty vault verification. Handles OCR receipt scanning, Cardano blockchain proof-of-purchase logging, immutable decision logging, agent collaboration discovery, and smart wallet payments. Use for warranty claims, product verification, agent-to-agent service payments, or immutable audit trails on Cardano.

Surface markets where Simmer's AI price diverges from Polymarket. High divergence = potential alpha. Use when user wants to find AI vs market disagreements, scan for trading opportunities, or understand where the AI is bullish/bearish relative to external prices.

Security-first command execution for AI agents. Classifies commands by risk level (SAFE→CRITICAL), enforces transparency, prevents dangerous operations. Includes enforcement scripts and agent integration patterns.

Complete A-Z Discord server administration. Channel/role/member management, AutoMod, webhooks, templates, audit logs, scheduled events, threads, and full server control via CLI.

When the user wants to add, fix, or optimize schema markup and structured data on their site. Also use when the user mentions "schema markup," "structured data," "JSON-LD," "rich snippets," "schema.org," "FAQ schema," "product schema," "review schema," or "breadcrumb schema." For broader SEO issues, see seo-audit.

Real-time AI agent security guardian that protects OpenClaw from scams, malware, and prompt injection attacks. Scan ClawHub skills before installing to detect malicious patterns (341+ known threats). Verify URLs, domains, and crypto wallet addresses for phishing and fraud. Monitor agent behavior for psychological manipulation (Cialdini P1-P6) and agent-to-agent social engineering. Generate SHA-256 legal evidence chains for suspicious interactions. Works as a continuous bodyguard, not just a one-time scanner. "When OpenClaw works, Scam Guards watches." Triggers: "is this safe", "scan skill", "check URL", "verify wallet", "security audit", "detect scam", "protect agent", "scan for malware", "check this link".