locate-ui-from-code

SUSPICIOUS. The skill’s capabilities are broadly aligned with its stated UI-debugging purpose, and its referenced tooling is mostly official or standard. The main risk is operational: it gives the agent strong browser and shell abilities to interact with a live app, persist overlays, and save evidence, while processing untrusted UI content. No clear credential harvesting, third-party proxying, stealth, or malicious exfiltration is present, so this is not malware, but it is a medium-risk skill.