story-review

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow reads the user’s provided manuscript text (e.g., “Read the full draft…” / “Read linearly…” guidance for editorial/developmental/copyedit/line/proofreading) and then performs analysis/reporting on that content, so outsider-authored free text can be ingested whenever a caller supplies it.