Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 91% confidence
- Finding
- The skill explicitly performs network-capable actions by scanning a user-provided website, discovering links, and proposing recurring health checks, yet no permissions are declared. This creates a mismatch between actual capability and declared security posture, reducing transparency and making it easier for network access to occur without appropriate review or policy gating. In this context the network use is core to the skill’s function, so the issue is not hidden malicious behavior, but it is still a real security weakness because the skill can reach arbitrary user-supplied URLs and later automate repeated checks.
