competitor-branding

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

• Third-party content exposure detected (high risk: 0.85). The required workflow explicitly instructs the agent to “Pull from their website, social profiles, ads, and any available materials” for competitors, which at runtime can involve fetching/reading outsider-authored web pages or social content and injecting their free-form text into the LLM context.