The Agent Skills Directory

[SAFE]: The skill defines a strict execution workflow that utilizes local CSV files for routing and markdown playbooks for analysis. It does not attempt to access sensitive file paths, perform network operations, or execute arbitrary commands.
[SAFE]: The skill references various well-known technology organizations and academic sources (such as Cloudflare, Stripe, Anthropic, and the W3C) to ground its auditing heuristics. These references are purely informational and do not involve the download or execution of remote code.
[SAFE]: While the skill is designed to ingest and process untrusted user documentation for auditing, it lacks high-risk capabilities—such as file-system writes or network exfiltration tools—that would allow an indirect prompt injection attack to compromise the host environment.

docs-audit