visual-report
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted audit findings, saved reports, and manual data into HTML dashboards. Ingestion points include raw skill output, saved reports, and manual data metrics (Step 1). These points lack explicit boundary markers or instructions to sanitize/escape data before interpolation into the HTML output. The skill has the capability to write these files using the Write tool. While data is normalized, there is no explicit verification of content safety against XSS or similar injection vectors within the generated reports.
- [EXTERNAL_DOWNLOADS]: The skill fetches the Chart.js library from the jsDelivr CDN (https://cdn.jsdelivr.net/npm/chart.js). This is a well-known service, and the skill instructions follow security best practices by recommending pinned versions and the inclusion of Subresource Integrity (SRI) hashes in the generated HTML dashboard.
- [COMMAND_EXECUTION]: The skill utilizes allowed Bash tools (Grep, cat, ls, npm view) to analyze existing audit files and verify package versions. These tools are restricted to reading data and verifying dependencies in line with the skill's primary purpose of reporting.
Audit Metadata