@hmharness/agent@0.13.2
hmharness agent execution layer: base tools, system prompt, sub-agent spawn, and the shared task runner that frontends (cli, web) drive.
AI security review
scanned · by lpm-firewall-aiThe source contains real high-impact agent capabilities, so it merits a warning as dangerous dual-use functionality. No source evidence establishes malicious install-time behavior, theft, persistence, or covert execution.