marketing-context

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflows explicitly direct the agent to ingest and analyze public third-party sources — e.g., the "Customer Research Methodology" (product reviews, community forums, social listening) and "Content & SEO Context"/"Competitive Analysis Framework" (external URLs, competitor site copy and meta descriptions) — which are untrusted/user-generated sources that the agent is expected to read and use to influence messaging and decisions.