Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 92% confidence
- Finding
- The skill describes and encourages use of capabilities that access environment variables and perform outbound network requests, but it does not declare corresponding permissions. Undeclared capabilities weaken auditability and sandbox/policy enforcement, which can let an agent use secrets such as webhook URLs or signing secrets and send data externally without clear user visibility.
