mongodb-natural-language-querying

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data which could potentially contain malicious instructions.
  • Ingestion points: The skill ingests external data using mcp__mongodb__find to fetch sample documents and mcp__mongodb__collection-schema to retrieve field names (SKILL.md).
  • Boundary markers: The instructions include a specific 'Anti-Patterns' section that explicitly warns the agent against treating external content, logs, or tool responses as trusted instructions (SKILL.md).
  • Capability inventory: The skill utilizes read-only MongoDB MCP tools for listing databases, collections, indexes, and schemas, as well as performing find queries (SKILL.md).
  • Sanitization: The agent is instructed to validate all field references against the fetched schema before generating queries to prevent unexpected behavior (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:52 AM
Security Audit — agent-trust-hub — mongodb-natural-language-querying