macos-capabilities

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a technical reference for macOS development and does not include any executable scripts or hidden code.- [SAFE]: Information regarding persistence (Launch Agents) and system entitlements is provided for developer guidance on legitimate platform features and does not target the agent's host environment.- [SAFE]: The skill is limited to a read-only toolset (Read, Glob, Grep) for reviewing project files, which mitigates the risk of unauthorized system modifications through indirect prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 01:19 PM
Security Audit — agent-trust-hub — macos-capabilities