stitch-mcp-get-screen

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches user-requested HTML code, high-resolution screenshots, and Figma assets from official Google Stitch download endpoints (stitch.google.com).
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through its multi-source data ingestion pipeline.
  • Ingestion points: User-provided project/screen paths, HTML source code retrieved from the Stitch API, and local configuration files (contracts, APIs, examples) read from related framework skills (e.g., stitch-uviewpro-components).
  • Boundary markers: Absent. The instructions do not define specific delimiters or instructions for the agent to ignore potentially embedded commands within the fetched HTML or reference files.
  • Capability inventory: The skill utilizes the Read tool to access the local file system and stitch tools to communicate with external APIs.
  • Sanitization: Absent. There is no specified logic for validating or escaping the content retrieved from external or local sources before it is processed by the agent for code generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 10:44 AM