Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 89% confidence
- Finding
- The skill declares no explicit permissions while instructing the agent to execute shell commands (`bash .../forecast.sh` and `bash .../cities.sh`). This creates a transparency and policy gap: reviewers and runtime controls may underestimate the skill's actual capabilities, increasing the chance of unintended command execution or insufficient sandboxing of external network activity.
