anti-slop-design
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains purely instructional content related to UI/UX design and frontend development. It provides specific heuristics, CSS standards, and design archetypes (Quiet Luxury, Technical Dense, Editorial, Warm Tactile) for engineering production-ready software.
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for auditing and refactoring user-provided code and design assets. While this creates a potential surface for indirect prompt injection, the risk is managed by the skill's internal quality gates and its specific focus on design tokens rather than logic execution.
- Ingestion points: The skill ingests UI code and screenshots for diagnostic audits and style extraction (Phase 1, Cure 1).
- Boundary markers: The skill does not explicitly define delimiters for untrusted input data.
- Capability inventory: The agent is authorized to write and modify CSS variables, Tailwind classes, and DOM structures across the project files (Phase 1-4).
- Sanitization: No explicit sanitization of ingested content is defined; the skill relies on its "7-Axis Pre-Emit Quality Gate" to validate the output integrity.
Audit Metadata