to-tickets-plus

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md:11-11 requires fetching and reading the full body/comments of a user-passed reference (e.g., an issue id or URL), which can pull in outsider-authored free text from public web content or third-party issue/comment threads into the agent’s LLM context.