anti-slop-frontend
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses external user-provided briefs to determine UI layout and aesthetic, creating an ingestion point where instructions embedded in data could potentially influence agent behavior.
- Ingestion points: User-provided design brief (SKILL.md).
- Boundary markers: Absent.
- Capability inventory: The skill directs the agent to install external packages and generate UI code (SKILL.md).
- Sanitization: No validation or sanitization of brief content is mentioned.
- [EXTERNAL_DOWNLOADS]: The skill references placeholder images from the well-known picsum.photos service and recommends installing official design system packages (such as Material, Carbon, or Tailwind) from public registries.
Audit Metadata