product-design
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed of markdown-based instructions and templates designed to guide an agent through information architecture, user flow mapping, and wireframe specification. It contains no executable scripts, network requests, or commands that interact with the host system.
- [DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or data exfiltration patterns were detected. The skill operates on product design requirements and produces documentation for human review.
- [PROMPT_INJECTION]: The instructions are strictly process-oriented. No attempts to override system safety guidelines or ignore previous instructions were found.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from product discovery artifacts (e.g., PRDs, user stories). However, the output is limited to structured documentation and Mermaid diagrams for human review. The process includes a 'Log Read-Back' step and a 'Human Review Gate', which serve as natural validation and boundary markers against adversarial input in the requirements documents.
Audit Metadata