mongodb-natural-language-querying

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill instructs the agent to fetch and use sample documents that "show actual data values" and to produce stringified query filters (which may embed exact field values), so if those samples contain API keys, tokens, or passwords the LLM could be required to output them verbatim.