@titan-design/active-work@0.25.0
Durable workspace state for engineering work — CLI, MCP, and Claude skill for tracking initiatives across sessions
AI security review
scanned · by lpm-firewall-aiThe postinstall hook automatically installs the package’s own Claude Code skill and command outside the package directory, which is an agent extension lifecycle risk. The reviewed code did not show credential theft, unrelated network contact, or broader agent configuration changes.