writing-zenn-articles

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (INSTRUCTIONS.md Step 0 and Step 0.5) explicitly instructs using WebFetch or a browser to read public Zenn pages (https://zenn.dev, https://zenn.dev/trending, and https://zenn.dev/topics/{タグ名}), which are user-generated/untrusted third-party sources that the agent must interpret to choose titles and tags and thus can materially influence subsequent actions.