@hmharness/agent@0.23.34
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 manifest has no install hook, and the inspected runtime behavior is consistent with a coding-agent library. The flagged project reads, report writes, Git operations, and query-based search show no package-controlled credential transfer or other concrete attack behavior.