prisma-client-api-raw-queries

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for handling external data within database queries, demonstrating both safe and unsafe patterns for educational purposes.
  • Ingestion points: The skill illustrates data ingestion through variables like userInput in SKILL.md.
  • Boundary markers: It uses explicit code comments such as // ✅ Safe and // ❌ SQL injection vulnerability! to guide the agent toward secure practices.
  • Capability inventory: The skill enables full database access including SELECT, INSERT, UPDATE, and DELETE operations via the Prisma client in SKILL.md.
  • Sanitization: It promotes the use of tagged template literals for automatic parameterization and Prisma.sql for building dynamic queries securely.
  • [DYNAMIC_EXECUTION]: The skill documents the use of Prisma.raw() and $queryRawUnsafe for executing dynamically generated SQL strings, which are standard features of the Prisma library for runtime query construction.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 12:05 AM
Security Audit — agent-trust-hub — prisma-client-api-raw-queries