seo

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

• Third-party content exposure detected (high risk: 0.75). Step 2 performs live checks by fetching arbitrary deployed-site pages (e.g., raw HTML via curl for evidence, plus robots.txt, sitemap.xml, and llms.txt), so outsider-authored free text from the public web can be ingested into the agent’s LLM context as “evidence” snippets.