improve-app
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely through natural language instructions, guiding the agent to interact with the user and manage documentation in a
docs/folder. It focuses on UX heuristics, product positioning, and design principles. - [EXTERNAL_DOWNLOADS]: The skill mentions a fallback command
npx skills add wondelai/skills/<slug> --globalif a sub-skill is missing. This is presented as an optional instructional step for the user rather than an automated execution path, and it targets the author's own namespace. - [COMMAND_EXECUTION]: There are no automated command executions or scripts. The skill's primary function is to manage local markdown artifacts (
CUSTOMER.md,DESIGN.md,EXPERIMENTS.md, etc.) based on user input. - [PROMPT_INJECTION]: No patterns of instruction override, safety bypass, or role-play injection were detected. The instructions are focused on adherence to the nine-phase improvement methodology.
Audit Metadata