ads

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and extracts content from arbitrary public websites via the required /ads dna <url> workflow (see references/brand-dna-template.md "Extraction Guide" which instructs scanning homepage/about/product and public ad libraries), and that extracted third-party content (brand-profile.json) is then consumed by downstream steps (ads-create, ads-generate) to influence prompts, image generation, and campaign decisions.