mobile-design
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where user-supplied descriptions of app purpose, target audience, and brand feeling are processed and translated into generated design tokens and screen layout code.
- Ingestion points: User inputs for app category, audience, and visual feeling in the SYSTEM and SCREEN modes as defined in the SKILL.md documentation.
- Boundary markers: The skill does not implement specific delimiters or instructions to isolate user-provided text from the agent's core instructions.
- Capability inventory: The skill directs the agent to generate and "emit" TypeScript or NativeWind token modules, providing a mechanism for user-controlled strings to be written directly into the project's source files.
- Sanitization: There are no explicit instructions for the agent to sanitize, validate, or escape user-supplied descriptions before they are incorporated into the emitted design system specifications.
Audit Metadata