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 processes normalized profile datasets derived from public social-media sources (see SKILL.md "Collect platform data" which references skills/20-research/tiktok-research, instagram-account-research, x-research, plus lead-schema.md sourceUrls and scripts like scripts/build_creator_leads.mjs) — these are untrusted, user-generated public profile pages whose text and metadata are read and directly drive scoring and outreach-drafting decisions.