axiom-test-simulator

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses xcrun simctl to manage simulator states, capture screenshots, and simulate hardware events. It also uses killall -9 Simulator as a recovery mechanism for unresponsive processes.
  • [EXTERNAL_DOWNLOADS]: Instructions include the option to install AXe, a UI automation tool, via Homebrew (brew install cameroncooke/axe/axe). This involves downloading code from a public GitHub repository, which is a well-known service used for package distribution.
  • [INDIRECT_PROMPT_INJECTION]: The skill is instructed to read configuration from .axiom/preferences.yaml. This represents a data ingestion point where externally provided values (device names and UDIDs) are incorporated into the agent's context. Boundary markers are absent for this ingestion, but the risk is low as the data is scoped to simulator identifiers.
  • [DATA_EXPOSURE]: The skill accesses simulator logs and system crash reports located in ~/Library/Logs/DiagnosticReports/. While these files contain system state information, access is local and intended for the skill's primary purpose of debugging test failures.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 10:58 AM
Security Audit — agent-trust-hub — axiom-test-simulator