Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 95% confidence
- Finding
- The skill declares no permissions while explicitly instructing the agent to run a shell setup script and use a local SQLite-backed CLI that writes under ~/.nex-onboarding/. This creates a transparency and consent gap: users and policy engines may not realize the skill can execute shell commands and persist files, increasing the chance of unintended code execution or local data modification.
