Loading...
Loading...
Found 60 Skills
Add policy enforcement, zero-trust identity, and execution sandboxing to AI agents with Microsoft's Agent Governance Toolkit
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations.
Security-first skill vetting for AI agents. Use before installing any skill from community, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
Comprehensive security auditor for AI agent skills, prompts, and instructions. Checks for typosquatting, dangerous permissions, prompt injection, supply chain risks, and data exfiltration patterns — before you use any agent or skill.
Security audit enforcement for AI agents. Automated security scans and health verification.
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for prompt-injection, retrieval poisoning, memory contamination, planner drift, MCP or tool-boundary abuse, and agent exfiltration challenges. Use when the user asks to analyze prompt injection, retrieval poisoning, memory contamination, planner drift, tool-argument corruption, or secret exposure caused by an agent chain. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
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.
Validates permission inheritance between parent and child agents. Ensures child permissions are equal to or more restrictive than parent. Activate on 'validate permissions', 'permission check', 'inheritance validation', 'permission matrix', 'security validation'. NOT for runtime enforcement (use dag-scope-enforcer) or isolation management (use dag-isolation-manager).
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.
Review prediction-market, basket, oracle, and trading-agent workflows for compliance, safety, data-quality, privacy, and execution risk. Use before any workflow handles venue auth, user portfolio data, API keys, or trade planning.
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?".
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.