creator-outreach

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and acts on public social-media profile and post data (see SKILL.md "2. Collect platform data" which requires normalized datasets from platform research skills, and references/routing.md which lists public scraper actor routes like clockworks/tiktok-scraper and apidojo/twitter-user-scraper), and the scripts (e.g., build_creator_leads.mjs, score_creator_leads.mjs) parse sourceUrls, scrapedAt, sourceEvidence, and comment/content signals to score leads and drive outreach—so untrusted user-generated content from third-party sites can materially influence agent decisions.