visual-report
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's HTML template (
assets/base.html) loads Tailwind CSS and Mermaid.js from well-known and reputable services (cdn.tailwindcss.com and jsdelivr.net). - [COMMAND_EXECUTION]: The skill instructions direct the agent to generate and write self-contained HTML files (
report-<topic>-YYYY-MM-DD.html) to the project root directory. - [DATA_EXPOSURE]: The skill is designed to read local codebase files, documentation, and version history to synthesize business logic for the generated reports. This access is limited to internal analysis for report generation.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted data from the codebase and interpolates it into an HTML report.
- Ingestion points: Project source code, documentation files, and git history as specified in the 'Legwork' step.
- Boundary markers: None explicitly defined to separate ingested data from report structure.
- Capability inventory: File system write access to create the HTML report.
- Sanitization: The 'Audit' step focuses on ensuring business terminology rather than technical sanitization of the generated output.
Audit Metadata