shape
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a high-level planning assistant. It guides the AI through two phases: a discovery interview (delegated to another skill,
grill-me) and the synthesis of a design brief. - [SAFE]: File access is limited to reading project documentation (e.g.,
PRODUCT.md,DESIGN.md) and design system files (CSS, tokens) to ground the AI in the project's existing style. No sensitive directories are targeted. - [SAFE]: The skill does not perform any network operations, download external scripts, or include obfuscated content. The frontmatter correctly uses
disable-model-invocation: true, indicating it is a text-based guidance skill rather than a tool-executing one.
Audit Metadata