@hmharness/agent@0.14.6
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-aiInspected source shows task-context reading, pipeline report writing, explicit search requests, and project-scoped command execution. No install lifecycle hook, credential exfiltration, or concrete malicious behavior was found.