brand-voice

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow ingests outsider-authored free text only if the user-supplied source material is fetched (e.g., via x-api for “recent original X posts and threads” or via “real inbound emails or DMs”), but this skill document itself does not specify any unconditional outsider text ingestion path.