Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 83% confidence
- Finding
- The skill documentation indicates network and environment-backed capabilities but does not declare corresponding permissions. That creates a transparency and governance gap: users and reviewers cannot accurately assess what data may be accessed or transmitted, especially when personal stats queries depend on stored usernames and remote API access. In a skill ecosystem, undeclared capabilities are dangerous because they bypass least-privilege review and make downstream misuse harder to detect.
