What it does
This entry points to one SKILL.md file in the publisher's library of 818 cybersecurity skills for AI agents, each written in the agentskills.io open format. Going by its file path, this skill covers security scanning of infrastructure-as-code. The library maps its skills to frameworks such as MITRE ATT&CK and NIST CSF 2.0, based on each skill's type.
Someone would reach for this skill when they want an AI agent to follow structured guidance on checking infrastructure-as-code for security issues during a security review.
To use it, clone the library and point an agent at the file. The library states it works with Claude Code, GitHub Copilot, OpenAI Codex CLI, Cursor, Gemini CLI, and other agentskills.io-compatible platforms.
Limitations and requirements
Community project, not affiliated with Anthropic PBC. The library includes offensive and dual-use techniques and is stated to be for authorized penetration testing, security research, defense and education only. Use only against systems you own or have explicit written permission to test, and comply with applicable laws and rules of engagement. The publisher states that users are solely responsible for how they use the skills.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
Sources
- AgentSkillsDir first seen 13 Nov 2026 · last seen 18 Nov 2026 · its page on the source
Review source
As shown on agentskillsdir.com when we last read it