mongodb-schema-design

Pass

Audited by Gen Agent Trust Hub on Nov 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill interfaces with the MongoDB MCP server to perform database operations including schema inference and query analysis as documented in SKILL.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted database metadata and logs to provide schema optimization advice.
  • Ingestion points: Schema definitions and slow query logs ingested via MCP tools (SKILL.md).
  • Boundary markers: Features an Action Policy section in SKILL.md requiring explicit user confirmation for write operations.
  • Capability inventory: Includes database read, write, and administrative capabilities via mcp__mongodb__ tools.
  • Sanitization: Enforces human-in-the-loop review for all potentially destructive or state-changing operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 20, 2026, 08:35 AM