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 directly fetches and parses public X/Twitter content (e.g., fetchHomeHtml in scripts/http.ts and fetchXTweet/fetchXArticle / fetchTweetDetail in scripts/graphql.ts which call https://x.com and abs.twimg.com) and interprets user-generated tweets/articles (including extracting IDs, cursors, and features from responses) as part of its workflow, so untrusted third-party content can materially influence subsequent requests and output generation.