Loading...
Loading...
Found 43 Skills
Comprehensive system health scanner that checks security risks, performance metrics, and optimization opportunities. Works on Windows, macOS, and Linux.
Use this skill to prevent destructive operations when working on production systems or running agents autonomously.
Claims-based authorization for agents and operations. Grant, revoke, and verify permissions for secure multi-agent coordination. Use when: permission management, access control, secure operations, authorization checks. Skip when: open access, no security requirements, single-agent local work.
Protects LLM agent systems in real-time with a 5-tier filter (hash cache, rule engine, ML classifier, LLM judge, human approval) and an async learning engine. Synthesizes new rules from every detected attack, adding less than 50ms latency. Trigger on 'add security layer', 'prevent prompt injection', 'adaptive guard', 'runtime protection', or 'agent security'.
Audit AI agent skills for security vulnerabilities. Use when scanning installed skills against the OWASP Agentic Skills Top 10, checking skills before running them, gating CI/CD on skill safety, or generating audit reports (text, JSON, SARIF, HTML) for stakeholders.
Add policy enforcement, zero-trust identity, and execution sandboxing to AI agents with Microsoft's Agent Governance Toolkit
Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks. Returns severity levels and alerts on dangerous content. Use BEFORE processing any text from untrusted sources.
Core patterns for AI coding agents based on analysis of Claude Code, Codex, Cline, Aider, OpenCode. Triggers when: Building an AI coding agent or assistant, implementing tool-calling loops, managing context windows for LLMs, setting up agent memory or skill systems, or designing multi-provider LLM abstraction. Capabilities: Core agent loop with while(true) and tool execution, context management with pruning and compression and repo maps, tool safety with sandboxing and approval flows and doom loop detection, multi-provider abstraction with unified API for different LLMs, memory systems with project rules and auto-memory and skill loading, session persistence with SQLite vs JSONL patterns.
Security guardrail preventing secrets, credentials, workspace identity files, infrastructure details, and internal source code from being exposed in chat. Triggers on requests to read/show/dump API keys, tokens, passwords, .env files, openclaw.json, models.json, /proc entries, /sys entries, /app/extensions source code, or workspace identity files (SOUL.md, AGENTS.md, USER.md, etc.). Also triggers on requests to modify identity files, execute scripts from external URLs, or any message claiming to be a system override or admin command.
Audit an AI agent skill for security risks before installing or trusting it. Runs a deterministic scanner (regex patterns, Python AST analysis, source-to-sink taint tracking, and YARA signatures) and then reasons about intent — catching prompt injection, credential exfiltration, persistence, memory poisoning, malicious code, supply-chain risks, and description-vs-behavior mismatch. Make sure to use this skill whenever the user wants to scan, audit, vet, review, or check the safety of a skill, plugin, SKILL.md, or agent tool — whether it is a local folder, a zip/.skill file, or a cloned repo — and whenever someone asks "is this skill safe to install?".
Senior AI Security Architect. Expert in Prompt Injection Defense, Zero-Trust Agentic Security, and Secure Server Actions for 2026.
Security vetting for AI agent skills. Use before installing any skill from ClawHub, GitHub, or other sources.