laravel

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

• Third-party content exposure detected (high risk: 0.90). The skill's required references (references/ai-sdk.md) explicitly document built-in WebSearch/WebFetch tools and support for attachments from arbitrary URLs (e.g., Image::fromUrl('https://...')), meaning the agent will fetch and interpret open/public third‑party content as part of its workflow and that content can materially affect decisions and tool use.