cloudkit
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill includes code and examples that fetch and process user-generated CloudKit content from publicCloudDatabase and sharedCloudDatabase (e.g., records(matching:), CKQuery/CKFetchRecordZoneChanges, CKAcceptSharesOperation and subscription callbacks), so the agent would ingest and interpret untrusted third‑party data from other users/public records.
Audit Metadata