stitch-mcp-get-screen

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references asset download URLs from stitch.google.com. These are legitimate resources from a well-known service used for UI design-to-code workflows.
  • [DATA_EXPOSURE]: The skill processes project and screen identifiers provided by the user to fetch UI code. These identifiers are used solely for the intended function of the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests HTML code and design metadata retrieved from external screens to perform framework conversion.
  • Ingestion points: Screen HTML code retrieved from the Stitch API and reference documentation from local skill directories (e.g., stitch-uviewpro-components).
  • Boundary markers: None identified in the prompt templates.
  • Capability inventory: The skill uses Read, Write, and stitch*:* tools to process design data and generate code files.
  • Sanitization: No explicit sanitization of the retrieved HTML is described before it is used for code generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 04:13 AM
Security Audit — agent-trust-hub — stitch-mcp-get-screen