Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 88% confidence
- Finding
- The skill clearly instructs the agent to execute a bundled shell script, but the skill metadata does not declare any tool scope or allowed-tools restriction. That mismatch is dangerous because it can cause an agent or host environment to run shell-capable actions without an explicit least-privilege boundary, increasing the risk of unintended command execution or abuse if the script or surrounding inputs are modified.
