kotlin-multiplatform-skill-harvester

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

• Third-party content exposure detected (high risk: 0.85). The required workflow reads outsider-authored free text from consumer-provided docs/lessons/*.md (and lesson issue bodies, per SKILL.md) at runtime via harvest_lessons.py using path.read_text(...), then includes extracted summaries/errors in the generated harvest report that is shown to the user/used for amendment drafting.