playbook-ai-specificity

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests outsider-authored free text by fetching a “plain homepage” (meta description + first 1,500 chars) and/or a rendering-proxy extraction for an outsider’s arbitrary domain to produce the Company Description / Rendered Fetch evidence used by the AI writer.