wordpress-live-validation

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

• Third-party content exposure detected (high risk: 0.85). The skill ingests outsider-authored free text from the target WordPress post URL at runtime: it navigates to a user-supplied {post_url} and then extracts rendered DOM text (e.g., document.body.innerText for placeholder/draft text and h1/h2 text) via browser_evaluate, which becomes LLM context.