Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 82% confidence
- Finding
- The skill advertises shell and network-capable behavior via local scanning and VirusTotal integration, but the metadata declares no permissions or equivalent trust boundary information. This is dangerous because users and reviewers cannot accurately assess that the skill may execute local tooling and send data externally, increasing the risk of unreviewed command execution or data exfiltration.
