core-data

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill contains functions that ingest untrusted user input for database queries.
  • Ingestion points: User-provided search strings in searchUsers(query:) and UserList(searchText:) within SKILL.md.
  • Boundary markers: The code samples explicitly use parameterized format strings (%@) and the #Predicate macro, which serve as secure boundaries between the query logic and the data.
  • Capability inventory: The skill manages local application data via Core Data and SwiftData (Create, Read, Update, Delete).
  • Sanitization: The skill promotes the use of built-in framework sanitization methods to prevent injection into data queries.
  • [SAFE]: The instructions and code snippets follow iOS development best practices, emphasizing secure query construction and appropriate thread safety for background operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 08:10 PM
Security Audit — agent-trust-hub — core-data