The Agent Skills Directory

[SAFE]: The skill serves as a purely instructional guide for performing security audits. It documents defensive practices based on the OWASP Top 10 and other security standards.
[DATA_EXPOSURE]: Mentions of sensitive file paths like .env or .ssh are strictly for auditing purposes, instructing the agent to verify that such files are not committed to source control.
[COMMAND_EXECUTION]: References to shell commands like grep or package audit tools (npm audit, pip-audit) are provided as standard methodology steps for a human or agent to follow during a security review.
[PROMPT_INJECTION]: No instructions were found that attempt to bypass AI safety guidelines or override system instructions.

security-audit-standard