Tp4
- Category
- MCP Tool Poisoning
- Confidence
- 91% confidence
- Finding
If the implementation really lacks the advertised API generation, architecture diagram generation, and broad sync behavior, then the skill overstates what it does and may cause users or agents to trust it for actions it cannot safely or correctly perform. Misrepresentation of behavior is dangerous in agent skills because operators may grant write access or automation authority based on inaccurate expectations.
- Content
