teach-unit

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

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md the required runtime workflow performs a “frontier scan of the unit’s .tickets/” and then a “work/ scan” that reads all homework submissions (the learner’s) from work/ in order to create homework-feedback tickets, which means outsider-authored free text can be ingested without selecting a specific item.