managing-database-schemas

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard shell commands (cat, ls, grep, find) to detect ORM configurations and read schema definitions from the local filesystem.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx to execute commands from established database management ecosystems, specifically Prisma, Drizzle-kit, and TypeORM. These are well-known technology tools and their usage is consistent with the skill's primary purpose.
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by processing external source code files during schema analysis.
  • Ingestion points: Reads files such as prisma/schema.prisma, src/db/schema.ts, and entity files found in src/**/*.ts.
  • Boundary markers: None; the content is processed directly for structural analysis.
  • Capability inventory: File system access via shell utilities and execution of ORM CLI tools via npx.
  • Sanitization: None; the skill relies on the agent's interpretation of the schema data.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 11:33 PM