draft-ui-redesign
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill identifies an ingestion surface as it processes local source code and API response definitions to perform its UI audit, which is the primary purpose of the skill. Ingestion points: Source files (route handlers, components) and sample API response data defined in Phase 1 of SKILL.md. Boundary markers: The prompt template includes a constraint block instructing the design tool to follow the content inventory, although no explicit delimiters are defined for the audit process itself. Capability inventory: File system write access to docs/redesign/ for generating redesign specifications; no network or shell execution capabilities are utilized. Sanitization: The skill follows a strict 'contract' that prohibits modifying application logic or existing API contracts, acting as a procedural mitigation.
- [EXTERNAL_DOWNLOADS]: The README provides standard installation instructions pointing to the author's public repository on GitHub. This is consistent with standard skill deployment practices. Evidence: https://github.com/mshindi-labs/agent-skills.
Audit Metadata