database-design-quality-review
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for static analysis of database designs (ERDs, DDL, etc.) and contains multiple explicit instructions to avoid dangerous operations. Both
SKILL.mdandprompts/database-design-quality-review.mdmandate that the agent must not connect to real databases, execute migrations, or run benchmarks. The workflow incorporates a structured 'Input Audit' (known, missing, conflicting, etc.) which serves as a cognitive boundary for processing untrusted user data. The evaluation cases specifically test the agent's ability to refuse production connections and unauthorized command execution. No suspicious network operations, obfuscation, or persistence mechanisms were detected. The design prioritizes redacted data and evidence-backed inferences, minimizing the risk of data exposure.
Audit Metadata