What it does
This entry is a SKILL.md file from the Anthropic Cybersecurity Skills library, a collection of structured cybersecurity skills for AI agents. The file's subject is implementing secret scanning with gitleaks.
Someone would reach for it when they want an AI agent to follow structured, skill-based guidance on secret scanning with gitleaks, instead of working from general prompts. The library holds 818 skills across 34 security domains, and each skill follows the agentskills.io open standard.
To use it, clone the library and point the agent at it. The publisher states that the library works with Claude Code, GitHub Copilot, OpenAI Codex CLI, Cursor, Gemini CLI, and any agentskills.io-compatible platform.
Limitations and requirements
The publisher describes this as an independent community project, not affiliated with Anthropic PBC. The library includes offensive and dual-use techniques, which the publisher says may be used only on systems the user owns or has explicit written permission to test, in line with applicable laws and rules of engagement. The user is solely responsible for how the skills are used.
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