@hmharness/agent@0.14.14
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 registry-install lifecycle hook, and the inspected source shows workspace context discovery, pipeline persistence, agent web search, and project command execution without a concrete attack chain. The static similarity and structure hints are not supported by malicious behavior in these excerpts, so the package is clean.