py-migrate

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate guidance for database schema management using industry-standard tools like Alembic and SQLAlchemy. No malicious patterns such as prompt injection, data exfiltration, or obfuscation were identified.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it instructs the agent to read model definitions and database schemas to generate migrations.
  • Ingestion points: Reads Python model files (e.g., src/infrastructure/postgres/models.py) and database state via Alembic.
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: Executes shell commands (alembic) and modifies the filesystem by creating migration files.
  • Sanitization: Relies on the developer's manual review of autogenerated migration scripts as recommended in the 'Core principle' and 'Common Mistakes' sections.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 05:03 AM
Security Audit — agent-trust-hub — py-migrate