ai-content-quality-checker

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly accepts and processes arbitrary article/HTML/text inputs provided at runtime (e.g., usage examples like "[記事全文]", "[HTML]", and "[記事]"), so it ingests untrusted third‑party/user‑provided content that the agent will read and interpret.