product-launch-announcement-writer

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly instructs "If user provides a GitHub repo or homepage: Use available web search and page-reading tools to analyze" — the skill therefore fetches and reads arbitrary public GitHub repos and homepages (untrusted, user-generated content) and uses that content to shape drafts and next actions.