safe-migrations

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it is designed to ingest and process database migration files from the local file system.
  • Ingestion points: Database schema and migration files located in paths such as db/** and **/db/**.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined for the processed data.
  • Capability inventory: The skill allows for the generation and execution of database schema modifications and raw SQL through the execute method.
  • Sanitization: While the skill provides high-level warnings against SQL injection, it lacks automated sanitization or validation logic for data processed from migration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 04:38 AM
Security Audit — agent-trust-hub — safe-migrations