idea-probe
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill operates entirely through structured prompting and persona simulation. It does not include any executable scripts, binary files, or external code dependencies.
- [SAFE]: The skill follows an internal 'honesty contract' that explicitly warns users that its outputs are simulations, not market evidence. This prevents deceptive claims about validation.
- [SAFE]: All external URLs referenced in the documentation (README.md) point to the official GitHub repositories of the author ('m1nga') for related tools (scenario-probe, product-experience-officer, extend-first). These are legitimate vendor resources used for cross-linking skills.
- [SAFE]: The skill provides a shell command in the README (
npx skills add m1nga/idea-probe) for installation. This is a standard procedure for adding AI agent skills via a package manager and does not involve suspicious remote execution patterns. - [SAFE]: No sensitive data exposure, credential handling, or obfuscation techniques were found. The prompt instructions are transparent and follow best practices for role-play and simulation without attempting to bypass safety filters.
Audit Metadata