What it does
This entry points to a single SKILL.md file for performing steganography detection, taken from a community-created library of 818 structured cybersecurity skills. The library follows the agentskills.io open standard and is designed to give an AI agent structured guidance on security tasks.
The library is described as usable 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 the agent at it. The publisher's documentation for this specific skill is not included in the source, so details of its method are not described here.
Limitations and requirements
The publisher states that the library includes offensive and dual-use techniques, intended only for authorized penetration testing, security research, defence and education. Use is permitted only against systems the user owns or has explicit written permission to test, and the user must comply with applicable laws and rules of engagement. The publisher says the user is solely responsible for how the skills are used. The project is independent and 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