modeling-conversion-metrics
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies event names and properties as untrusted ingestion data.
- Ingestion points: Event names and property keys in the database events table.
- Boundary markers: Instructions specify treating these as quoted data rather than instructions.
- Capability inventory: Use of tool-based view creation for persistent storage.
- Sanitization: Requires use of schema verification tools before modeling.
Audit Metadata