honor-aid-check

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

• Third-party content exposure detected (low risk: 0.10). Source: SKILL.md defines a workflow that only ingests student/course-provided policy text and then classifies the student’s requested help, so outsider-authored free text is read only after the student supplies it as the request/context rather than from a monitored external feed/queue.