mongodb-natural-language-querying
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from MongoDB collections to inform its generation process, creating a surface for indirect prompt injection.
- Ingestion points: The skill fetches schema and document samples using
mcp__mongodb__collection-schemaandmcp__mongodb__findwithinSKILL.md. - Boundary markers: Absent; there are no clear delimiters or instructions to ignore potential commands within the sampled database documents.
- Capability inventory: The skill possesses the capability to generate MongoDB queries and aggregation pipelines which are intended for user execution.
- Sanitization: Absent; no validation or filtering is performed on the ingested sample data to prevent it from influencing the model's instructions.
Audit Metadata