prisma-schema

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill uses official Prisma documentation links and follows industry standard patterns for database schema management.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as a template generator that uses user input to create schemas which are subsequently processed by database tools. This creates an attack surface for schema-based confusion.
  • Ingestion points: User-provided model definitions and entity names via the $ARGUMENTS placeholder.
  • Boundary markers: No explicit delimiters or warnings to ignore embedded instructions are included in the generated output.
  • Capability inventory: Suggests running shell commands including prisma validate, prisma generate, and prisma migrate dev.
  • Sanitization: The skill relies on the agent's understanding and Prisma's internal validation rather than providing specific sanitization rules for user-provided identifiers.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 11:22 AM
Security Audit — agent-trust-hub — prisma-schema