kelly-deal-scorer

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a deterministic scoring rubric using plain arithmetic in scorer-model.js, ensuring all financial calculations are auditable and free from LLM-based manipulation.
  • [SAFE]: Sensitive operations, such as provisioning and decision execution, are isolated in dedicated management scripts that utilize environment variables for credentials, preventing the exposure of API keys in the source code.
  • [SAFE]: The web application (AirApp) includes robust HTML escaping in app.js and accent-theme.js to sanitize data ingested from Busabase records, protecting the user interface from potential cross-site scripting (XSS).
  • [SAFE]: The skill defines a narrow and appropriate set of permissions in its configuration, strictly limiting access to the specific Busabase resources required for deal scoring and review workflow.
  • [SAFE]: The project structure and dependencies align with the standard Busabase App-in-Skill framework, with no unauthorized network activity or suspicious code patterns detected across the scripts and frontend code.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 10:36 AM
Security Audit — agent-trust-hub — kelly-deal-scorer