@loop-lang/loop

One or more suspicious static signals were detected.

npm install -g @loop-lang/loop

Unconsented modification of future Claude Code behavior via installed /loopflow skill

postinstall copies Claude Code skill into ~/.claude/skills/loopflow

On a global install, npm runs the package postinstall hook. That hook checks npm_config_global and then copies the bundled Claude Code skill to ~/.claude/skills/loopflow, changing an AI-agent control surface outside the package directory without a prompt. The skill appears package-aligned, but the install-time write itself is the confirmed behavior.

Although the package is otherwise transparent and lacks exfiltration or destructive behavior, the global postinstall hook performs an unconsented lifecycle write into Claude Code's skill directory. Under the firewall policy, lifecycle AI-agent control-surface mutation is block-worthy even when the payload is package-aligned. Product guard normalized a concrete AI-agent control hijack publish_block to the blockable dangerous-capability shape.