ads-dna

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow (Step 2: "Fetch Pages" using the WebFetch tool) instructs the agent to fetch and return visible text, style blocks, meta tags and og:image values from arbitrary public website URLs provided by the user, and Step 3 uses that untrusted third-party page content to construct brand-profile.json which directly influences later ad-generation behavior.