seo-content-marketing-claude-skill-suite

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to crawl and analyze arbitrary public websites and SERP/backlink data (e.g., /content-audit --url https://example.com/blog, /technical-seo https://example.com, /page-speed-seo https://example.com/page, /serp-monitor --url example.com/blog and "Fetching keywords …"), which clearly ingests untrusted third‑party web content and uses it to drive audits, recommendations, outreach, and other agent actions.