@hmharness/agent@0.14.5
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-aiNo malicious lifecycle, hidden payload, secret collection, or package-initiated exfiltration was found. The package nevertheless exposes a broad set of high-impact agent capabilities, so it warrants a warning rather than a clean verdict.