Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 84% confidence
- Finding
- The skill explicitly documents network-backed behavior, including a remote API base URL and commands that validate credentials against a backend, but it does not declare corresponding permissions or clearly surface that network access is required. This can mislead users and policy systems about the skill's effective capabilities, reducing informed consent and weakening review controls around outbound data flow.
