react-vite-dashboard
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the Stitch platform and local DESIGN.md files to generate code. While no specific sanitization or boundary markers are defined (ingestion points: DESIGN.md, stitch:get_screen), the skill includes quality checklists and security guidelines to mitigate risks. The agent utilizes file system and shell access to perform its functions (capability inventory: Write, Bash, Read). \n- [EXTERNAL_DOWNLOADS]: The skill references documentation on stitch.withgoogle.com and suggests using the @google/design.md package. These resources are associated with Google, a well-known and trusted technology provider.
Audit Metadata