Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 87% confidence
- Finding
- The skill advertises shell execution and likely file-writing behavior via the recommended `python scripts/ziwei_chart.py ...` command and optional chart export, but it declares no permissions. This creates a capability/permission mismatch that can cause the agent to run code or write files without explicit user or platform approval, increasing the risk of unintended command execution, unsafe argument handling, or unauthorized file creation.
