ecc-foundation-models-on-device

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill references a workflow that involves executing scripts from openclaw-ecc/scripts/ as a fallback mechanism. This is a standard pattern for providing tool-backed functionality within an agent skill environment.
  • [SAFE]: The provided code examples and instructions follow official documentation patterns for Apple Intelligence. There are no signs of prompt injection, data exfiltration, or obfuscation. The skill encourages evidence-based reporting and deterministic execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 06:04 PM
Security Audit — agent-trust-hub — ecc-foundation-models-on-device