loki-mode@11.146.0
An autonomous software factory that knows what it is supposed to deliver, and proves it did.
AI security review
scanned · by lpm-firewall-aiThe reachable postinstall hook writes shell completions and can update the package’s own Claude skill link without a separate user command. These are bounded setup actions rather than evidence of credential theft or malicious remote execution, but automatic shell and agent-skill setup warrants a warning.