Tp4
- Category
- MCP Tool Poisoning
- Confidence
- 98% confidence
- Finding
The skill description promises a task-delegation assistant with optional AI-HIVE/MCP-backed execution, but the documented behavior appears centered on offline validation and references to external connection flows without clearly implementing the stated transformation/output behavior. This mismatch can mislead users or orchestration systems into invoking the skill in inappropriate contexts, causing unsafe overtrust, skipped review, or incorrect assumptions about what external actions were or were not actually performed.
- Content
