@theglitchking/hit-em-with-the-docs@3.1.2
Self-managing documentation system with hierarchical structure, intelligent automation, pattern discovery, and agent orchestration
AI security review
scanned · by lpm-firewall-aiThe package automatically writes Claude skills and a SessionStart hook into the consumer project during postinstall. This is an install-time change to agent configuration outside the package without explicit consent, so it is malicious under the AI-agent control hijack rule.