swiftdata
Pass
Audited by Gen Agent Trust Hub on May 24, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation contains links to 'sosumi.ai' for Core Data and SwiftData documentation. While this is not an official Apple domain, these are provided as informational references and do not involve the download or execution of remote scripts or active content.
- [SAFE]: No security issues were identified across the 10 threat categories. The skill's functionality is limited to defining local data models and performing standard CRUD operations.
- [DATA_EXFILTRATION]: No patterns indicative of data exfiltration or unauthorized network communication were found.
- [PROMPT_INJECTION]: The skill does not contain instructions aimed at overriding agent behavior or bypassing safety protocols.
- [INDIRECT_PROMPT_INJECTION]: The skill describes data ingestion through standard SwiftData fetch mechanisms. The ingestion point is the persistent store (SQLite), and the capability inventory is limited to standard data management. Framework-level sanitization in predicates reduces risks associated with untrusted data processing.
Audit Metadata