tech-blog-seo-rewriter

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly accepts and auto-loads article URLs and competitor article URLs (FORMS.md: "記事パス ... または記事URL", REFERENCE.md: "記事のURLまたは全文を取得", and optional "競合記事URL"), and also ingests user-provided/exported GSC data and CSVs from public sources, so the agent would read untrusted public web content as part of its workflow.