stitch-ui-react-vite-dashboard
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows security best practices by explicitly instructing the agent to avoid handling sensitive credentials like passwords or private keys, and to use demo data for reports.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external HTML and image data from the Stitch platform. It mitigates injection risks through mandatory pre-flight checks, clarifying intent with the user, and utilizing validation checklists to ensure output consistency and safety. Evidence Chain: 1. Ingestion points: Stitch HTML and screenshots (SKILL.md, workflow.md). 2. Boundary markers: Workflow steps for clarifying intent and validation checklists (SKILL.md, references/validation-checklist.md). 3. Capability inventory: File creation for React components and execution of Stitch MCP tools (SKILL.md, workflow.md). 4. Sanitization: Instructions to replace customer data with demo values and desensitize screenshots/files (SKILL.md, references/faq-deep.md).
- [EXTERNAL_DOWNLOADS]: The skill references and downloads assets from the official Stitch platform and GitHub repositories associated with Google Labs. These are well-known and project-relevant sources.
Audit Metadata