swiftdata-expert-skill

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Prompt Injection (SAFE): No instructions found that attempt to override agent safety or extract system prompts.
  • Data Exposure & Exfiltration (SAFE): No evidence of hardcoded credentials, sensitive file access, or unauthorized network operations. External links point to official Apple documentation.
  • Obfuscation (SAFE): Content is clear and readable; no Base64, zero-width characters, or homoglyph-based encoding detected.
  • Unverifiable Dependencies (SAFE): No external package installations or remote script executions are requested.
  • Privilege Escalation (SAFE): No commands requiring elevated privileges or modifications to system configurations.
  • Indirect Prompt Injection (SAFE): The skill analyzes local project code via 'rg' (ripgrep) to provide advice. While this constitutes an ingestion surface for user-controlled data, the skill lacks high-risk capabilities (such as network access or automated file modification) that would allow for exploitation.
  • Command Execution (SAFE): Uses standard search commands ('rg') for code inspection, which is consistent with the primary purpose of a development assistant and poses no risk to the host system.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:36 PM