seo-mastery-jp

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

• Third-party content exposure detected (high risk: 0.90). Flagged because the audit workflow and examples explicitly instruct fetching and analyzing arbitrary public websites (e.g., curl -s https://example.com/robots.txt, curl -s https://example.com/ | grep ..., npx lighthouse https://example.com, and "このサイトのSEO監査をして"), which requires the agent to ingest and interpret untrusted third‑party web content.