ios-simulator-automation

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a robust runtime ledger system in scripts/runtime_manifest.py that uses regex-based filtering (SENSITIVE_REFERENCE, SENSITIVE_ENVIRONMENT_KEY) to identify and reject the capture of sensitive data such as tokens, passwords, and OTPs.
  • [SAFE]: Execution of shell commands is confined to the preflight script scripts/check-simulator-environment.sh, which uses standard system utilities (xcrun, lsof, df) to verify local environment readiness without making unauthorized external connections.
  • [SAFE]: The skill's documentation in references/authenticated-flows.md provides proactive security guidance, explicitly instructing the agent to keep credentials and tokens out of all logs, screenshots, and manifests.
  • [SAFE]: Python and shell scripts included in the skill are well-structured, lack obfuscation, and rely exclusively on standard libraries or pre-installed platform tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 11:18 AM
Security Audit — agent-trust-hub — ios-simulator-automation