Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 87% confidence
- Finding
- The skill clearly directs file reads/writes and network crawling, yet no explicit permissions model is declared. That mismatch can cause an agent or reviewer to underestimate the skill's effective access, especially because it can read cookies, fetch logged-in pages, and persist account-derived data locally. In this context, the missing declaration is not inherently malicious, but it weakens transparency and consent around sensitive operations.
