database-schema-designer
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes user-provided natural language requirements to generate database schemas, migrations, and application code. This creates a surface for indirect prompt injection where malicious instructions embedded in requirements could influence the generated output.
- Ingestion points: Natural language requirements processed in the 'Schema Design Process' (SKILL.md).
- Boundary markers: Absent. The skill does not define specific delimiters or instructions to ignore embedded commands in the input data.
- Capability inventory: Generates DDL, migration scripts (SQL/Alembic), and ORM code (Drizzle/Prisma) (SKILL.md).
- Sanitization: Absent. No validation or filtering of input requirements is described.
Audit Metadata