kb-ai-review-lite

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

• Third-party content exposure detected (medium risk: 0.65). SKILL.md describes reading KB files’ body text via cat_file and then generating LLM output from that extracted content; since KB files are not guaranteed to be authored by the operating user, this can ingest outsider-authored free text (e.g., wiki/issues/third-party docs) into LLM context.