prisma-expert

Pass

Audited by Gen Agent Trust Hub on Nov 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands such as npx prisma, grep, and ls to perform environment detection, schema validation, and migration status checks. These operations are standard diagnostic tasks for a developer assistant and are limited to the project scope.
  • [EXTERNAL_DOWNLOADS]: The instructions include multiple links to the official Prisma documentation website (prisma.io). These are well-known and trusted resources for the skill's primary purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided content, such as Prisma schemas and TypeScript application code, to provide optimization and design advice. This represents a standard surface for indirect prompt injection common to developer tools.
  • Ingestion points: The agent reads project files like prisma/schema.prisma and relevant application source files provided by the user.
  • Boundary markers: The instructions do not define specific delimiters for separating user-provided code from the agent's instructions.
  • Capability inventory: The skill possesses the ability to execute shell commands (npx, grep, ls, psql) and provide code suggestions.
  • Sanitization: No explicit sanitization or filtering of user-provided schema content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 1, 2026, 11:35 PM