verify-claims

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

• Third-party content exposure detected (low risk: 0.10). Exclusion: the skill “verify-claims” only audits claims found in the user-specified workspace path or the assistant/session evidence it already has, and then performs optional explicit external lookups per claim; it does not continuously ingest outsider-authored free text from queues/feeds at runtime.