neon-vercel-postgres
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for processing external user data in database queries, representing a standard indirect injection surface.
- Ingestion points: User-supplied variables interpolated into SQL queries in
SKILL.md,templates/neon-basic-queries.ts, andtemplates/drizzle-queries.ts. - Boundary markers: The skill strongly recommends the use of SQL template tags to delimit data and prevent command injection.
- Capability inventory: The skill facilitates database read, write, and schema modification operations across
SKILL.md,scripts/test-connection.ts, andtemplates/neon-basic-queries.ts. - Sanitization: The instructions recommend input validation using Zod and rely on the automatic escaping provided by the recommended database clients.
Audit Metadata