@pushary/agent-hooks@1.9.216
Human-in-the-loop (HITL) for AI agents: ask a person for approvals or answers by push notification. One command connects Claude Code, Codex, Cursor, Gemini CLI and more.
AI security review
scanned · by lpm-firewall-aiThe network and remote-agent behavior matches Pushary’s stated purpose, and phone instructions reach the Claude agent only in remote control mode. The scanner’s npm and Stripe credential leads resolve to command-risk classification logic, not code that reads or sends those credentials.