post-to-x

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

• Third-party content exposure detected (high risk: 0.80). The skill's md-to-html.ts explicitly parses user-provided Markdown and "automatically download[s]" remote images (and supports cover_image as a URL), then converts/pastes that HTML into the X Articles editor—i.e., it fetches and ingests untrusted third-party content from arbitrary URLs as part of its workflow.