clone-website
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes data from external websites (Phase 1, Phase 3), creating an indirect prompt injection surface. A malicious target site could attempt to influence agent behavior via hidden content. Ingestion occurs during reconnaissance and component extraction. No explicit boundary markers or sanitization steps are defined for the ingested HTML/CSS data.
- [COMMAND_EXECUTION]: Employs standard developer tools and commands (
npx playwright install,npm run build,wget) to set up the environment and download assets. These commands are consistent with the skill's primary purpose of web development and cloning. - [EXTERNAL_DOWNLOADS]: Utilizes
curlandwgetto fetch media assets (images, videos) from the target URL. This behavior is documented and necessary for the website cloning functionality.
Audit Metadata