@pushary/agent-hooks@1.9.198
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 reviewed behaviors align with the package’s stated human-in-the-loop agent approval purpose: setup installs its own skill, and phone control uses the Pushary API key with Pushary agent endpoints. No lifecycle hook or unrelated credential destination was identified.