loki-mode@11.127.0
An autonomous software factory that knows what it is supposed to deliver, and proves it did.
AI security review
scanned · by lpm-firewall-aiThe inspected critical exfiltration and metadata indicators did not establish an attack chain. The default postinstall does make user-level completion changes and can repoint Loki's own Claude skill link, so this fits the warning-level agent extension lifecycle risk.