taste-design
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted user data to generate design specifications, representing an indirect prompt injection attack surface.
- Ingestion points: The skill analyzed project intent and "vibe descriptions" provided by the user in
SKILL.md(Section 1) to dynamically generate design guidelines. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands within user-provided descriptions are specified in the analyzed instructions.
- Capability inventory: The skill uses
StitchMCP,Read, andWritetools to generate and modify design system documentation. - Sanitization: The instructions do not define any sanitization, validation, or escaping logic for the external project descriptions before they are interpolated into the design system logic.
Audit Metadata