seo-engine

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

• Third-party content exposure detected (high risk: 0.90). The skill's required "Analyze Website URL" workflow in SKILL.md (using scripts/prepare_input/fetch_html.py, fetch_robots_txt.py, fetch_sitemap.py) and multiple rules (e.g., CLOAKING_DETECTION, HIDDEN_TEXT_DETECTION, KEYWORD_STUFFING, MALWARE_HOSTING_DETECTION) explicitly fetch and parse arbitrary public websites/URLs and use that untrusted content to drive rule selection, pass/fail decisions, and suggested fixes, so third-party content can materially influence the agent's actions.