content-opensource-project-article-writer

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

• Third-party content exposure detected (high risk: 1.00). The skill's workflow (SKILL.md Step 2) explicitly instructs the agent to "访问项目 GitHub 页面，阅读 README 和文档", which requires fetching and interpreting untrusted, user-generated content from public GitHub/GitLab pages that can materially influence generation and subsequent actions.