Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 87% confidence
- Finding
- The skill instructs the agent to execute a local Python script that reads and writes files and performs network requests, but the skill declares no permissions. This creates a permission-model mismatch: users or higher-level policy may believe the skill is low-risk while it can access the filesystem, write downloaded content, and contact external services, which weakens transparency and review controls.
