natural-language

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides documentation for official, on-device Apple frameworks including NaturalLanguage, Translation, and Core ML. It does not include any external dependencies, remote script executions, or unauthorized network calls.- [SAFE]: All data processing is described as occurring locally on the device, ensuring that sensitive financial transaction memos and PII do not leave the local environment.- [SAFE]: The skill promotes defensive security practices, such as using NLTagger's named entity recognition to redact PII from text before it is processed for logging or analytics.- [SAFE]: No obfuscation, hardcoded credentials, malicious persistence mechanisms, or dynamic execution of untrusted code were detected in the instructions or code examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 09:01 PM
Security Audit — agent-trust-hub — natural-language