tweet-ideas-generator

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly accepts user-provided URLs and instructs "If the user provides a URL, use WebFetch to retrieve the content" (Step 1), meaning the agent will fetch and analyze arbitrary public web content and thus can be exposed to untrusted third‑party/user‑generated content.