Skills
Navigate
skills/iwanhe/pandawa/database-schema-designer/Gen Agent Trust Hub

database-schema-designer

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [CREDENTIALS_UNSAFE]: The documentation includes a TypeScript example for database seeding that uses a hardcoded password string.
  • Evidence: passwordHash: await hashPassword('password123') in SKILL.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill generates complex database structures and RLS policies directly from user requirements without explicit instructions to ignore embedded malicious instructions.
  • Ingestion points: User requirements for database design in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: Generates SQL DDL, RLS policies, TypeScript types, and Python models.
  • Sanitization: Absent.
  • [EXTERNAL_DOWNLOADS]: The skill recommends using external visualization and schema tools via npx.
  • Evidence: npx prisma-erd-generator, npx @dbml/cli, and npx dbml-to-mermaid in SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 02:33 PM
Security Audit — agent-trust-hub — database-schema-designer