thetacog-mcp@2.42.0
Geometric-Driven Development (GDD) toolkit: cognitive rooms + Shadow Agent hooks + Ghost-Read pipeline (6 routes, persona-monologue) + thetacog-iterate convergence loop (meta-rule-checker, auto-applies high-confidence rewrites, adaptive stall-softening) +
AI security review
scanned · by lpm-firewall-aiThe lifecycle hook creates real unconsented local execution risk, including an opaque shipped native binary, but source inspection did not establish exfiltration, destructive behavior, remote payload execution, or foreign/broad AI-agent control hijacking. This fits a warning rather than a block under the stated policy.