The Agent Skills Directory

[SAFE]: The skill performs its stated purpose of regulatory auditing without attempting unauthorized actions, privilege escalation, or persistence. It identifies gaps in compliance frameworks and provides remediation guidance based on established regulatory standards.
[EXTERNAL_DOWNLOADS]: The skill references documentation and guidance from established regulatory and standards organizations, including the FTC, W3C, and the California Attorney General. These are trusted sources for compliance information.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface because it ingests untrusted data from external websites and local codebases during the audit process.
Ingestion points: The skill uses WebFetch to read content from arbitrary URLs and Glob/Grep to read local file content.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the data being analyzed.
Capability inventory: The skill uses Read, Glob, Grep, and WebFetch to gather information and generates a markdown report as its primary output.
Sanitization: The instructions do not provide specific sanitization or filtering logic for the ingested external content.

compliance-audit