narrative-enablement-kit

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

• Third-party content exposure detected (medium risk: 0.30). At runtime, the skill ingests outsider free text from the user’s prompt/“target audiences … [User-provided]” and may also treat “pasted canon excerpt, bio draft, or spokesperson answer” as untrusted input when assembling the enablement kit, even though it primarily reads trusted internal canon.