create-artist

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly calls the web-search endpoint (Step 4e and Step 6: POST /api/research/web) and instructs the agent to parse those public web/social results and use them to populate socials and synthesize the knowledge base, so untrusted third‑party content can directly influence subsequent PATCHes and decisions.