The skill directs use of a third-party service without warning that personal reading inputs will be transmitted.
- Category
- Output Handling
- Confidence
- 96% confidence
- Finding
The skill directs the agent to send reading questions and birth details to an external MCP service without requiring disclosure or informed user approval. These inputs can reveal identifying information or sensitive relationship, health, and financial concerns, while the service's retention and handling practices are unspecified. The transmission serves the skill's stated purpose rather than demonstrating malicious exfiltration, but that legitimate purpose does not eliminate the privacy risk.
- Content
