brand-builder

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

• Third-party content exposure detected (high risk: 0.90). The skill's naming module explicitly requires running WebSearch and parallel web queries (e.g., conflict pre-screen, domain pre-check, social-handle checks) on public web pages and social media as part of its runtime workflow (see references/01-naming.md "Pre-Screen — run searches in parallel" and "run WebSearch per name"), so it ingests untrusted third‑party content that can change tool behavior and decisions.