Agent Owasp Compliance

This runs your AI agent codebase against the OWASP Agentic Security Initiative Top 10, a standard for autonomous agent security that's separate from general LLM safety. It scans for controls like input validation before tool execution (ASI-01), tool allowlists and argument validation (ASI-02), capability boundaries (ASI-03), and cryptographic agent identity instead of string names (ASI-07). Use it before production deployment or when someone asks "is my agent OWASP compliant?" The structured approach is helpful because agent security is genuinely different from chatbot security. You're checking whether your system prevents prompt injection at the tool layer, not just the LLM output layer, which matters when agents can execute code or call APIs.

skills.sh installs: 1.5K
GitHub stars: 41K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add github/awesome-copilot --skill agent-owasp-compliance --agent claude-code

Installs into .claude/skills of the current project.

Files

Agent OWASP ASI Compliance Check

Evaluate AI agent systems against the OWASP Agentic Security Initiative (ASI) Top 10 — the industry standard for agent security posture.

Overview

The OWASP ASI Top 10 defines the critical security risks specific to autonomous AI agents — not LLMs, not chatbots, but agents that call tools, access systems, and act on behalf of users. This skill checks whether your agent implementation addresses each risk.

Codebase → Scan for each ASI control:
  ASI-01: Prompt Injection Protection
  ASI-02: Tool Use Governance
  ASI-03: Agency Boundaries
  ASI-04: Escalation Controls
  ASI-05: Trust Boundary Enforcement
  ASI-06: Logging & Audit
  ASI-07: Identity Management
  ASI-08: Policy Integrity
  ASI-09: Supply Chain Verification
  ASI-10: Behavioral Monitoring
→ Generate Compliance Report (X/10 covered)