cybercentry-private-data-verification

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

• Third-party content exposure detected (high risk: 0.80). The skill submits user text to the external Cybercentry service and ingests its public, third-party verification results (via acp job create / acp job status and the returned deliverable fields and proof_url such as https://verify.cybercentry.io/...), and those integrity_status/proof values are used in the workflow to make decisions (e.g., granting access), so untrusted external content can materially influence agent actions.