seed-test-data

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill assists in generating test data by reading project-specific schema files and existing test patterns. It operates as a text-generation tool without performing network requests, file writes, or command execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing project-resident files that may contain untrusted content.
  • Ingestion points: Reads model definitions from prisma/schema.prisma, migration files, schema.rb, and existing factory files (*.factory.ts).
  • Boundary markers: None present; the skill lacks specific instructions to disregard embedded commands in the processed data.
  • Capability inventory: The skill only generates code suggestions and has no access to sensitive system tools or network capabilities.
  • Sanitization: No input validation or sanitization is performed on the ingested content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 11:12 AM
Security Audit — agent-trust-hub — seed-test-data