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 X/Twitter HTML, JavaScript bundles, tweet/article JSON and media (see SKILL.md usage and scripts/graphql.ts, http.ts, tweet-to-markdown.ts and media-localizer.ts), ingesting untrusted user-generated content which the workflow interprets to drive further fetches and downloads and thus can materially influence tool actions.