Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 90% confidence
- Finding
- The skill declares it requires an API key and invokes a Python script that will necessarily make outbound requests to xAI, but the skill metadata does not explicitly declare permissions for environment access and network use. This weakens reviewability and consent because users and tooling may not get a clear, enforceable signal that the skill can read secrets and transmit data externally.
