baoyu-danger-x-to-markdown

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses public, user-generated X (Twitter) content (e.g., fetchHomeHtml calls https://x.com and graphql.ts uses https://x.com/i/api/graphql/fetchXTweet/fetchXArticle, and media-localizer downloads remote media URLs), and that untrusted content is interpreted and used to build requests, fetch referenced tweets, and drive downloads/file writes—so third-party content can materially influence tool behavior.