aptly@0.1.5
Model and reasoning recommendations for subagents, powered by the OpenAI Decisions API.
AI security review
scanned · by lpm-firewall-aiThe postinstall automatically writes an enabled agent-spawn hook and MCP registration into existing Codex or Claude host settings. This is install-time modification of AI-agent control surfaces outside the package directory, so it warrants a block despite its opt-out and CI safeguards.