prisma-expert

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses utility commands like 'npx prisma', 'ls', and 'grep' to perform environment checks, validate schema files, and manage database migrations. These are standard operations for development workflows.\n- [PROMPT_INJECTION]: The skill processes project-specific data including database schemas and migration SQL files, which serves as an ingestion point for indirect prompt injection.\n
  • Ingestion points: Processes 'prisma/schema.prisma' and files within the 'prisma/migrations/' directory (SKILL.md).\n
  • Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded prompts when reading schema or migration files.\n
  • Capability inventory: The skill can execute shell commands ('npx prisma', 'psql') and perform filesystem operations.\n
  • Sanitization: No specific sanitization or filtering logic is present for data ingested from the database configuration files.\n- [EXTERNAL_DOWNLOADS]: The skill includes references to official documentation from the Prisma website ('prisma.io') for guidance on schema design and migration management.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 09:48 PM
Security Audit — agent-trust-hub — prisma-expert