grade-and-review

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

• Third-party content exposure detected (low risk: 0.10). The workflow reads student submissions (code, essays, design docs) that the educator explicitly selects for grading at SKILL.md Suggested Process step 1, so learner-authored text is ingested only after the user chooses a specific item, with no automatic queue or feed that outsiders can post into.