to-tickets

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

• Third-party content exposure detected (high risk: 0.70). SKILL.md:11 says that if the user passes a reference (e.g., a spec path, issue number, or URL), the agent will fetch and read its full body and comments—this can ingest outsider-authored free text from public web pages or issues/threads at runtime.