chapter-architect

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

• Third-party content exposure detected (medium risk: 0.65). The skill ingests the “Research Dossier” (and other inputs) provided by other runtime skills/parties (e.g., research-assistant), and that dossier’s free-form research text can include outsider-authored content (e.g., scraped/public sources) that becomes LLM-readable context during Phase 1–5.