The Agent Skills Directory

[SAFE]: The skill operates as a read-only query generator. All external resources and tool names (mcp__mongodb__*) are consistent with the provided author (mongodb) and the skill's stated purpose. No obfuscation, persistence, or data exfiltration patterns were detected.
[COMMAND_EXECUTION]: The skill instructs the agent to use various MongoDB MCP tools (list-databases, list-collections, collection-indexes, collection-schema, and find) to gather context. These tools are used within the expected scope of query generation.
[PROMPT_INJECTION]: Indirect Prompt Injection Surface Detection:
Ingestion points: Untrusted data enters the agent context through the mcp__mongodb__collection-schema and mcp__mongodb__find tools (specified in SKILL.md).
Boundary markers: Absent. The skill does not provide delimiters or instructions to ignore potential commands embedded within the database samples or schema fields.
Capability inventory: The agent is granted access to the mcp__mongodb__* toolset for database interaction.
Sanitization: No validation or sanitization is performed on the data returned from the database before it is interpolated into the agent's reasoning process.

mongodb-natural-language-querying