agent-mongo

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill contains explicit examples and fallback instructions that put plaintext passwords on the command line (e.g., --password secret and --password <secret>), which would require the LLM to generate or echo secret values verbatim.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). MongoDB query/schema results are returned as NDJSON/JSON lines (including document field values and error hint strings) and are therefore outsider-authored free text originating from the database contents that the agent will read into the LLM context at runtime.