to-tickets

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

• Third-party content exposure detected (medium risk: 0.30). The SKILL’s runtime workflow only reads the existing conversation context and any user-provided referenced spec/issue/URL body, so outsider-authored free text can be ingested when the user supplies such references (e.g., posting an issue/URL whose full body/comments get fetched).