kelly-revshare-simulator
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it ingests scenario data (e.g., business names, decision notes) from Busabase bases which could potentially contain malicious instructions.
- Ingestion points: Data is fetched in
content/kelly-revshare-simulator-app/app/js/providers/busabase-provider.jsfrom thescenariosandsettingsbases. - Boundary markers: The application logic is primarily deterministic math, reducing the likelihood of instruction following from data, though UI labels are interpolated.
- Capability inventory: The skill has the capability to create, update, and delete records in Busabase via
records.changeRequestinbusabase-provider.js. - Sanitization: The application uses a robust
escapeHtmlutility incontent/kelly-revshare-simulator-app/app/app.jsandaccent-theme.jsto sanitize data before rendering it in the browser UI, mitigating XSS risks. - [SAFE]: The skill uses well-known Node.js packages (Hono, Busabase-SDK) and follows standard development practices. All external operations are scoped to the developer's Busabase environment. Sensitive credentials for setup scripts are managed through environment variables, which is a best practice.
Audit Metadata