drizzle-orm

Pass

Audited by Gen Agent Trust Hub on Oct 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of local database schema files and user-defined requirements to generate and execute migrations and queries, which represents a potential attack surface for indirect prompt injection.
  • Ingestion points: Inspection of the local Drizzle surface, including schema files, relations, and migration folders as described in the Workflow section of SKILL.md and references/usage-guide.md.
  • Boundary markers: The instructions do not provide explicit boundary markers or delimiters for untrusted schema content.
  • Capability inventory: The skill utilizes bunx drizzle-kit (described in references/kit-migrations.md) for generating and applying migrations, and the Drizzle client (described in references/schema-queries.md) for executing SQL against the database.
  • Sanitization: No specific sanitization or validation logic is requested for user-provided identifiers or SQL fragments within the instructions, although the skill emphasizes reviewing generated SQL as a best practice in references/kit-migrations.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 3, 2026, 11:13 AM