stitch-mcp-generate-screen-from-text

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill manages an input surface for indirect prompt injection by transforming user-provided descriptions into structured prompts for a UI engine. It mitigates risk through a 'Structure Strategy' that organizes input into defined categories.
  • Ingestion points: User UI requirements processed in SKILL.md and referenced in examples.
  • Boundary markers: Structural delimiters ([Device], [Mode], [Style], etc.) are used to organize the resulting prompt.
  • Capability inventory: Accesses the generate_screen_from_text tool and standard Read/Write file permissions.
  • Sanitization: The skill relies on formatting instructions provided to the agent; no automated sanitization is applied to user-supplied text.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 08:32 AM