my-design-grade
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill establishes a design system and quality-control loop using local reference files. The instructions are focused on UI/UX improvements for specific internal dashboard projects and do not involve suspicious system or network operations.
- [PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection by instructing the agent to ingest and analyze source code or live URLs provided by the user. However, the scope is restricted to design critique and the agent lacks the high-privilege capabilities required for malicious exploitation of this surface.
- Ingestion points: Identification of target source paths or live URLs for UI review (SKILL.md).
- Boundary markers: The instructions do not define explicit delimiters to separate the external UI content from the grading logic.
- Capability inventory: Capabilities are limited to reading local documentation and generating suggested code changes for UI styling (Tailwind CSS/React).
- Sanitization: The skill does not include specific sanitization steps for the ingested UI data.
Audit Metadata