canghe-danger-x-to-markdown

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and parses public, user-generated X/Twitter content (see SKILL.md usage and scripts/graphql.ts which calls https://x.com API endpoints, plus scripts/media-localizer.ts which downloads remote media URLs), and that third-party content is ingested and used to drive parsing, download decisions, and conversion workflows — so untrusted content can materially influence tool behavior.