Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 93% confidence
- Finding
- The skill documentation declares capabilities to read environment variables, read credential files, write a token cache, and call Google APIs, but there is no explicit permission model communicated to users. This creates a transparency and consent problem: users may provide OAuth credentials and authorize broad calendar access without a clear upfront declaration of what resources the skill will access and persist.
