threads-keyword-search

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

• Third-party content exposure detected (medium risk: 0.30). The Threads skill navigates to https://www.threads.com/search/?q={keyword}&serp_type={filter}, waits for the page, then LLM/agent-executed JS (via document.documentElement.innerHTML) extracts SSR-embedded JSON containing post captions/user fields from the public search results, which include outsider-authored Threads content.