migrations

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and modification of source code files, which is a standard surface for indirect prompt injection in code-management agents.
  • Ingestion points: Reads database migration files in app/*/database/migrations/, apps/web/config/database.ts, and the auto-generated apps/web/app/core/database/schema.ts.
  • Boundary markers: None explicitly mentioned; the agent relies on the structured nature of the TypeScript/AdonisJS files.
  • Capability inventory: The skill employs Bash to run framework commands and Read, Write, Edit, Grep, and Glob for file operations.
  • Sanitization: Not applicable, as the skill is designed to handle developer-written code within a local project environment.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute specific AdonisJS framework commands (pnpm ace migration:fresh, pnpm ace migration:run, pnpm ace migration:status). These are legitimate administrative tasks for database schema evolution in a development context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 01:05 PM
Security Audit — agent-trust-hub — migrations