Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 92% confidence
- Finding
- The skill documentation describes capabilities that perform shell execution, network access, and local file writes, yet it declares no permissions or trust boundaries. In an agent setting, this can mislead operators and downstream policy systems about what the skill is able to do, increasing the risk of unintended command execution, credential storage, and external data exfiltration.
