@pushary/agent-hooks@1.9.226
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 manifest has no install hook, and the flagged credential requests use the Pushary key with the Pushary service for the package’s advertised agent approval and remote-control functions. Setup and agent polling are user-triggered or configuration-dependent; the inspected remote command path is restricted to remote mode with an active session.