network-pivoting-tunneling

This skill is coherent for its stated purpose, but the purpose itself is offensive security: it teaches an AI agent to pivot into internal networks, establish tunnels, and facilitate lateral movement. Install references mostly point to official or same-publisher tooling, so this is not strong evidence of malware, but it is a high-risk capability set for an AI agent and should be treated as a dangerous offensive-security skill rather than a benign workflow helper.