mongodb-natural-language-querying
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by ingesting untrusted data from external sources.
- Ingestion points: The skill uses
mcp__mongodb__collection-schemaandmcp__mongodb__findto read database structure and content into the agent context (SKILL.md). - Boundary markers: There are no specific instructions or delimiters to isolate the retrieved data from the agent's instructions.
- Capability inventory: The skill is restricted to the
mcp__mongodb__*toolset for database operations. It does not have access to general shell execution, network tools (curl/wget), or file system writes. - Sanitization: No sanitization or validation of the retrieved database content is performed before processing.
- [SAFE]: The skill's operations are consistent with its stated purpose of providing natural language querying for MongoDB. All external tools utilized are within the
mcp__mongodbnamespace, belonging to the vendor.
Audit Metadata