core-data
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external storage, creating a potential surface for indirect prompt injection.\n- Ingestion points: Managed object data is retrieved via
NSFetchRequestandNSPersistentHistoryChangeRequestas described inSKILL.md,references/core-data-patterns.md, andreferences/persistent-history.md.\n- Boundary markers: None provided; the skill lacks specific delimiters or warnings to ignore instructions embedded in stored data.\n- Capability inventory: The skill includes database write access (context.save()), batch deletion/insertion (context.execute()), and persistent history management across multiple files as shown inreferences/core-data-patterns.mdandreferences/persistent-history.md.\n- Sanitization: None provided; there is no guidance on sanitizing or validating data retrieved from the persistent store before it enters the agent's context.
Audit Metadata