mongodb-schema-design
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interfaces with external database content through MCP tools like
mcp__mongodb__findandmcp__mongodb__aggregate, which creates an inherent surface for instructions embedded in data to influence the agent. - Ingestion points: Collections and query statistics retrieved from the connected MongoDB instance.
- Boundary markers: The skill implements a robust "Action Policy" section that requires explicit user confirmation for any write or destructive operations, effectively maintaining a human-in-the-loop security model.
- Capability inventory: Access to database read/write tools via the MongoDB MCP server.
- Sanitization: Relies on user review of all generated commands before execution.
- [EXTERNAL_DOWNLOADS]: The skill recommends connecting the official MongoDB MCP server from a trusted GitHub repository (
github.com/mongodb-js/mongodb-mcp-server) for verification tasks.
Audit Metadata