system-fit
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is comprised entirely of markdown-based instructions for UX decision-making. It does not include any scripts, tools, or binary executables.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze project-specific data (e.g.,
.ux/DESIGN-SYSTEM.md, Storybook, and design documentation). - Ingestion points: Reads documentation and local system files within the project context.
- Boundary markers: Instructions include explicit commands to ground work in evidence and never invent rationale or requirements.
- Capability inventory: The skill does not possess any capabilities for subprocess execution, file system modification, or network requests.
- Sanitization: Not applicable, as the skill only produces textual recommendations based on existing project data.
- [METADATA_POISONING]: All metadata fields (name, description, author, version) are clear and align with the logic presented in the instructions. No deceptive patterns or hidden commands were found in the headers.
Audit Metadata