threads-blog-post

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

• Third-party content exposure detected (high risk: 0.90). The skill's Fetcher agent (described in SKILL.md and implemented in scripts/fetch_threads.py) explicitly crawls user-provided Threads.net/Threads.com URLs using agent-browser to extract post text, Open Graph/JSON-LD metadata and media (user-generated, untrusted third-party content) which is then consumed by the Content and Media agents to drive generation of blog posts and downloads—allowing that third‑party content to directly influence agent decisions and outputs.