industry-trends

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

• Third-party content exposure detected (high risk: 1.00). The skill's mandatory data-collection steps call get_inspo_creatives, get_creative_transcript, and get_inspo_brand_context (and related brand/competitor lookup APIs) to fetch competitor ad creatives and transcripts from external/public ad libraries or brand pages, and the agent is required to read and quote that untrusted third-party content as part of its analysis.