designing-database-schemas
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external business requirements and application source code, which constitutes an entry point for untrusted data.
- Ingestion points: Business domain requirements and application models/classes as mentioned in the Prerequisites and Instructions in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or prompts to distinguish between user data and instructions.
- Capability inventory: The skill is restricted to database client interaction (psql, mysql, mongosh) via the Bash tool, alongside standard file Read/Write/Edit capabilities.
- Sanitization: The skill does not explicitly describe input sanitization, but its specific domain focus on schema design limits the scope of actionable commands.
- [EXTERNAL_DOWNLOADS]: The skill references several external resources for educational and technical guidance.
- Evidence: URLs pointing to postgresql.org, wikipedia.org, and use-the-index-luke.com are provided in the Resources section. These are well-known, established technical and documentation sites.
Audit Metadata