@theglitchking/hit-em-with-the-docs@3.2.2
Self-managing documentation system with hierarchical structure, intelligent automation, pattern discovery, and agent orchestration
AI security review
scanned · by lpm-firewall-aiThe package's postinstall registers a SessionStart hook in the consumer project's Claude settings without an explicit user request. This is an install-time write to broader agent configuration, so it is malicious under the agent control-surface rule.