seo-images

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly asks for a target URL and its SKILL.md Phase 2 plus scripts/fetch_page.py and scripts/parse_html.py fetch and parse arbitrary public webpages (user-provided URLs) and then use that untrusted content to drive analysis and generated remediation code, so third-party page content can influence the agent's actions.