What it does
This entry points to a single skill file, SKILL.md, in the publisher's library of 818 structured cybersecurity skills across 34 security domains. The library follows the agentskills.io open standard. Based on its file name, the skill covers detecting attempts to exfiltrate data from Amazon S3 storage. The source material does not describe this skill's specific steps or outputs.
The skill suits security analysts and defenders who want an AI agent to provide structured guidance on S3 data exfiltration detection during an investigation. The publisher's documentation states that the library is intended for authorized penetration testing, security research, defense and education.
To use it, clone the repository and point an agent at the skill file. The publisher lists Claude Code, GitHub Copilot, OpenAI Codex CLI, Cursor, Gemini CLI and any agentskills.io-compatible platform as working with the library.
Limitations and requirements
The publisher states that the library is for authorized and lawful use only, against systems the user owns or has explicit written permission to test. The user is solely responsible for how the skills are used. The library is an independent community project 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