schema-migration-planner

Pass

Audited by Gen Agent Trust Hub on May 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely instructional and provides a framework for the AI to reason about database migrations. It does not contain executable code, scripts, hidden commands, or network operations.
  • [PROMPT_INJECTION]: The skill processes user-provided database schemas and migration code to generate its advice. While this represents a potential surface for indirect prompt injection (Category 8), the skill contains no malicious instructions and operates within normal agent parameters.
  • Ingestion points: User-provided database schema descriptions, code paths, and migration script requirements as specified in the Read First section of SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined for the input data.
  • Capability inventory: The skill generates text-based migration plans and does not define any direct tool interactions, shell execution, or system commands.
  • Sanitization: No explicit sanitization or validation of the input data is performed by the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 6, 2026, 10:14 AM
Security Audit — agent-trust-hub — schema-migration-planner