remix-chatgpt-ad-from-sample

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

• Third-party content exposure detected (high risk: 0.85). The skill ingests outsider-authored free text from the public/outsider “source sample” via get_ad_template { template_id: source_sample_id } → recipe.conversation / extracted_script (ChatGPT ad sample content authored by others), which is then used to derive the conversation and streamed assistant text that the LLM context will process during remixing.