Doukui (斗魁) - multi-provider AI agent orchestration harness for Claude Code: goal-driven agentic loop, dependency-graph dispatch, per-WP worktree isolation, for GLM/DeepSeek/MiMo and Claude
This report shows the evidence for doukui@0.5.0. 3 of 4 known versions are blocked or flagged. The newest version, 0.6.0, is flagged.
AI security review
scanned · by lpm-firewall-aiThe postinstall hook automatically installs skills and registers executable hooks in the user’s global Claude Code settings. This is an unconsented install-time change to an AI agent control surface, so the package is malicious under the agent configuration rule.