pentest-network-internal

SUSPICIOUS: the skill’s behavior is coherent with its stated purpose, but that purpose is to give an AI agent offensive internal pentest capability, including credential attacks and lateral movement. There is no direct evidence of credential theft to third-party servers or hidden malware, but the operational and misuse risk is high and external tool installation details are incomplete here.

This is documentation for a security-testing MCP toolset, not executable code. It describes legitimate but powerful dual-use operations, including credential harvesting, exploitation, arbitrary command execution, and filesystem changes. The documentation alone does not establish malicious intent or reveal whether access controls exist; deployment should restrict these tools to authorized users and targets.