tuzi-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 pages and API bundles (see scripts/http.ts and scripts/graphql.ts which call https://x.com and abs.twimg.com, and SKILL.md usage), then reads that content to build markdown, fetch referenced tweets, and download media (scripts/referenced-tweets.ts and scripts/media-localizer.ts), so untrusted third-party content is ingested and can materially influence further fetches, downloads, and file-write actions.