kelly-retail-intel
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from various untrusted external sources like weather feeds, news sites, and competitor pages. The potential for indirect prompt injection is mitigated by the skill's core design, which requires a human operator to review and approve all signals, actions, and drafts in a dedicated AirApp before they are acted upon. Furthermore, the AirApp frontend (app.js) correctly applies HTML escaping to data retrieved from these sources.
- [COMMAND_EXECUTION]: The skill includes administrative scripts (setup.mjs, publish_airapp.mjs, and execute_decisions.mjs) intended for local environment management and deployment to the Busabase platform. These scripts handle credentials securely via environment variables and perform expected management tasks without exposing arbitrary command execution paths.
Audit Metadata