docs-auditor
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill logic is entirely consistent with its described purpose. It uses structured evaluations and template-based reporting to provide documentation audits without any hidden or malicious behaviors.
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use web search and fetch tools to retrieve publicly accessible documentation content and configuration files (e.g., robots.txt, sitemap.xml, llms.txt). These downloads are necessary for the audit and target user-provided domains.
- [COMMAND_EXECUTION]: The skill utilizes platform tools to perform web-based operations and save resulting audit reports as HTML files to the local working directory, which is appropriate for its intended workflow.
- [PROMPT_INJECTION]: While the skill involves processing external web content which constitutes an indirect prompt injection surface, there are no instructions within the skill that attempt to bypass safety filters or override agent constraints.
Audit Metadata