hebrew-seo-geo-toolkit

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow includes fetching arbitrary outsider-authored web page text (the target URL’s HTML) via scripts/seo_audit.py → fetch_url(url) → resp.read().decode(...), which is then parsed and placed into the agent’s LLM context as audit output (meta tags/H1/JSON-LD counts/robots.txt contents).