narrative-landscape

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

• Third-party content exposure detected (high risk: 1.00). The skill's required inputs and Process step 3 explicitly direct the agent to extract positioning signals from public competitor messaging sources (company websites, advertising copy, social media profiles, press coverage, and specified URLs per "Competitor messaging sources" and Process step 3), which are untrusted third‑party sources the agent must read and that materially influence scoring and recommended actions.