workload-analysis

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs legitimate customer usage and revenue analysis by retrieving data from internal billing and CRM systems (Vitally and Postgres) using internal tools and SQL queries.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Vitally account traits and billing reports which are then interpolated into a React template for visualization.
  • Ingestion points: Vitally account data (vitally:get_account_full) and PostHog billing SQL results (postgres.prod.billing_usagereport) as defined in SKILL.md.
  • Boundary markers: No explicit boundary markers or "ignore embedded instructions" warnings are defined for the interpolated data.
  • Capability inventory: The skill generates and writes a local React component file ({account-name}-workload-analysis.jsx) containing the processed data.
  • Sanitization: No specific sanitization, escaping, or validation of external content is defined before it is interpolated into the React template.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 12:47 AM
Security Audit — agent-trust-hub — workload-analysis