Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 95% confidence
- Finding
- The skill clearly instructs the agent to use sensitive capabilities including environment access, file read/write, network access, and shell execution, yet it declares no permissions boundary. In practice this creates a broad, implicit trust surface: the agent could access cloud credentials, modify Terraform files, and run deployment/destruction commands without an enforceable least-privilege contract.
