What it does
This is a SKILL.md file from the Anthropic Cybersecurity Skills library, a collection of 818 structured cybersecurity skills for AI agents, each following the agentskills.io open standard. Based on its file path, this skill covers performing user behavior analytics.
Each skill in the library is mapped to the security frameworks relevant to its type, such as MITRE ATT&CK and NIST CSF 2.0. The library is intended to give an agent expert-level guidance during a security investigation, and it is listed as working with Claude Code, GitHub Copilot, OpenAI Codex CLI, Cursor, Gemini CLI and other agentskills.io-compatible platforms.
Running it involves cloning the repository and pointing an AI agent at the skill file.
Limitations and requirements
The publisher states that the library includes offensive and dual-use techniques, intended only for authorized penetration testing, security research, defense and education. Users should test only systems they own or have explicit written permission to test, and are responsible for complying with applicable laws and rules of engagement. The project is a community creation and is not affiliated with Anthropic PBC.
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