landing-page-generator
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it ingests untrusted content from repository documentation (e.g., README.md) and interpolates it into the generated landing page templates without explicit sanitization. \n
- Ingestion points: README.md, CHANGELOG.md, and other documentation files within the target repository. \n
- Boundary markers: Absent; content is extracted via patterns and mapped to placeholders. \n
- Capability inventory: Local file-system write operations to create the generated project folder. \n
- Sanitization: Absent; the skill does not explicitly sanitize extracted content before placing it into HTML templates. \n- [EXTERNAL_DOWNLOADS]: The generated search functionality (search.js) includes a dynamic script loader that fetches the MiniSearch library from the jsdelivr CDN. This is a standard and common practice for static sites. \n- [SAFE]: The generated GitHub Actions workflow utilizes official and well-known actions (actions/checkout, actions/configure-pages, etc.) for deploying the static site to GitHub Pages.
Audit Metadata