aptly@0.1.2
Model and reasoning recommendations for subagents, powered by the OpenAI Decisions API.
AI security review
scanned · by lpm-firewall-aiThe package’s postinstall hook automatically edits existing Codex and Claude configuration to register an MCP server and agent-spawn hook. This unrequested install-time change to AI-agent settings is malicious under the install-time control-hijack rule.