mongodb-natural-language-querying
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for generating read-only MongoDB queries and aggregation pipelines. It utilizes standard Model Context Protocol (MCP) tools to retrieve database metadata and sample records, which is necessary for its stated purpose. It includes specific guidelines for query optimization, field validation, and context size management to prevent excessive data consumption.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from a MongoDB database to assist in query generation. 1. Ingestion points: Field schema and sample documents are retrieved using mcp__mongodb__collection-schema and mcp__mongodb__find in SKILL.md. 2. Boundary markers: No specific delimiters are defined to isolate database content within the prompt context. 3. Capability inventory: The skill generates query strings but does not contain capabilities for file system access, network communication, or shell command execution. 4. Sanitization: Field names are validated against the fetched schema to ensure they exist before query generation.
Audit Metadata