pushary@1.9.124
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 flagged behaviors are consistent with Pushary’s stated purpose: setup detects tools, and agent hooks and wrappers communicate with Pushary using its own configured API key. The manifest declares no install lifecycle hooks, and the reviewed code showed no unrelated credential transfer or concealed execution.