@hmharness/agent@0.19.2
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-aiSource inspection found no install hook or concrete attack behavior. The flagged capabilities are consistent with an agent execution package, and the shell tool requires approval.
Decision evidence
public snapshot- package.json declares no install lifecycle hook; its only script is a build command.