What it does
This entry is a single SKILL.md file from the Anthropic-Cybersecurity-Skills library, a community collection of structured security skills for AI agents. Based on its file path, the skill covers hunting for abuse of single sign-on (SSO) tokens in SaaS applications. The publisher's documentation describes the library as following the agentskills.io open standard and mapping skills to frameworks such as MITRE ATT&CK and NIST CSF 2.0.
It would be relevant to security analysts who are investigating possible misuse of SSO tokens across cloud applications and want an agent to guide that work. The library describes its skills as expert-level guidance for security investigations.
To use it, clone the repository and point an agent that supports the agentskills.io format at the skill, such as Claude Code, GitHub Copilot, OpenAI Codex CLI, Cursor, or Gemini CLI.
Limitations and requirements
The library includes offensive and dual-use techniques intended only for authorized penetration testing, security research, defense and education. Use them only against systems you own or have explicit written permission to test, and comply with applicable laws and rules of engagement. 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 19 Nov 2026 · its page on the source
Review source
As shown on agentskillsdir.com when we last read it