lovstudio-find-logo

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow ingests outsider-authored free text in that the user-provided --name/--url can be used to fetch and parse HTML from https://{domain}/ to extract og:image/twitter:image and <link rel="icon"> during scrape_page_images() and subsequent http_get() probing, meaning arbitrary attacker-controlled input can drive LLM-readable parsing of returned page content.