one-source-of-truth
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill is instructed to locate and read declarative schema files (e.g., Prisma, Drizzle, SQL) and migration directories. This access is necessary for its stated purpose of auditing data models and maintaining a source of truth within the local codebase.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the codebase (schema definitions and code comments). It uses this information to build a concept inventory and audit reports. The risk is minimized as the skill focuses on structural analysis and documentation rather than executing logic embedded within the analyzed data.
Audit Metadata