Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 95% confidence
- Finding
- The skill declares no permissions, yet its documented commands and metadata clearly imply shell execution, network access, environment variable use, and local file reads/writes. This mismatch is a real security issue because it hides the skill's true capabilities from the permission model and from users, reducing transparency and undermining least-privilege review.
