x-bookmark-quote-posts

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow ingests outsider-authored free text from the user’s X bookmarks and authored post content by opening https://x.com/i/bookmarks and also expanding/referencing authored posts from https://x.com/<handle> / https://x.com/search?q=from%3A<handle>&src=typed_query&f=live without selecting specific items beyond using the bookmark feed.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs the assistant to open X pages at runtime (e.g., https://x.com/i/bookmarks) and ingest the fetched posts/bookmarks to calibrate voice and generate drafts, so external content directly controls the agent's outputs.