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). This skill autonomously fetches and parses user-generated content from the open web (X/Twitter at https://x.com) — see graphql.ts/fetchXTweet & fetchXArticle, thread.ts which reads cursors from API responses to drive additional fetches, media-localizer.ts which downloads remote media URLs, and main.ts which orchestrates these flows — so untrusted third‑party content is read and used to control subsequent requests and actions.