threads-user-posts

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

• Third-party content exposure detected (medium risk: 0.30). At runtime the skill navigates to a Threads profile page and ingests the page’s rendered HTML/GraphQL responses to extract each post’s caption text (including outsider-authored user content) via document.documentElement.innerHTML in scripts/extract-posts.py and via network POST https://www.threads.com/graphql/query responses after scrolling.