Tp4
High
- Category
- MCP Tool Poisoning
- Confidence
- 76% confidence
- Finding
- The skill's top-level description focuses on nutrient lookup, but the documented behavior also includes outbound requests to a third-party service and reading credentials from env/.env without making those behaviors prominent in the declaration. That mismatch can mislead users and automated policy systems about data flows and trust boundaries, increasing the risk of inadvertent secret exposure or unintended network use.
