Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 91% confidence
- Finding
- The skill documentation clearly instructs the agent to invoke Python scripts that perform network access, local logging, report generation, and shell-style piped execution, yet the skill declares no permissions. That creates a transparency and consent problem: users or platforms may not realize the skill can write persistent files and access the network, which can lead to unexpected data collection or policy bypass.
