ads-photoshoot

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

• Third-party content exposure detected (high risk: 0.70). The skill's Step 1 explicitly accepts a "product URL" (in addition to local files or text), which implies fetching/ingesting content from arbitrary public websites and using that untrusted content (images/descriptions) to build prompts that drive generation, so third-party content could materially influence actions.