Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 95% confidence
- Finding
- The skill clearly invokes shell-capable tooling (`python3`, `himalaya`, and `remindctl`) but does not declare permissions or clearly bound those capabilities. This creates a trust and enforcement gap: an agent may execute side-effecting commands without an explicit permission model, increasing the chance of unintended email sending or reminder creation.
