skills/marcioaltoe/skills/drizzle-orm/Gen Agent Trust Hub

drizzle-orm

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documents the installation of numerous standard and well-known database-related packages from the npm registry. These include the core drizzle-orm and drizzle-kit packages, as well as official drivers and adapters from trusted providers like Cloudflare, Vercel, Neon, Supabase, and AWS (e.g., @neondatabase/serverless, @vercel/postgres, @planetscale/database, @aws-sdk/client-rds-data).
  • [COMMAND_EXECUTION]: The documentation includes instructions for executing standard CLI commands using npx for database lifecycle management, such as drizzle-kit generate, drizzle-kit migrate, drizzle-kit push, and drizzle-kit studio. These commands are standard for development workflows with Drizzle ORM.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from databases, which represents a potential attack surface for indirect prompt injection.
  • Ingestion points: Data retrieved from database queries (e.g., db.select(), db.query.findMany()) and schema definitions imported from project files.
  • Boundary markers: The ORM architecture uses structured TypeScript builders and parameterized query logic to separate data from execution commands.
  • Capability inventory: The skill allows for comprehensive database operations, including writing to the file system (migration files via drizzle-kit) and making network requests to database servers via configured drivers.
  • Sanitization: Drizzle ORM primarily uses parameterized queries by default to prevent SQL injection. While the sql.raw() function is documented for specific use cases, it is accompanied by explicit warnings that it should only be used for trusted strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 11:33 AM