The Agent Skills Directory

[SAFE]: The skill is primarily focused on providing educational guidance and structured methodologies for conducting authorized security assessments, with an uncompromising emphasis on legal compliance and written authorization.- [COMMAND_EXECUTION]: The skill contains an instruction for the agent to check for missing companion skills by running ls on standard agent skill directories (e.g., ~/.claude/skills/). This environmental discovery is used solely for identifying internal dependencies within the AbsolutelySkilled ecosystem and does not involve unauthorized access or exfiltration of sensitive data.- [EXTERNAL_DOWNLOADS]: The skill recommends the installation of additional vendor-provided companion skills (e.g., appsec-owasp, cloud-security) from the author's official repository via npx. These are trusted resources intended to extend the agent's security capabilities.- [PROMPT_INJECTION]: The skill includes a behavioral instruction to start the first response with a 🧢 emoji to signal skill activation. This is a benign marker and does not attempt to bypass safety constraints or override the agent's core instructions.

penetration-testing