Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 92% confidence
- Finding
- The skill clearly directs the agent to execute shell commands (`which`, `npm install`, `cp`, `chmod`, `crontab`, `launchctl`, `rm`) but does not declare corresponding permissions. This creates a trust and review gap: users or policy systems may not realize the skill can modify the host environment, install software, and persist scheduled jobs.
