axe-ios-simulator

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [External Downloads] (MEDIUM): The skill requires the installation of the 'axe' CLI tool from an untrusted Homebrew tap (cameroncooke/axe/axe). Installing binaries from unverified third-party sources introduces a supply chain risk as the source code and build process are not audited.
  • [Command Execution] (LOW): The skill relies on executing system commands to interact with the simulator. While these commands are intrinsic to the skill's purpose, they provide a wide range of control over the virtual device, including hardware buttons and text input.
  • [Indirect Prompt Injection] (LOW): The skill features automation patterns that parse simulator UI content to drive logic.
  • Ingestion points: The skill reads the simulator's accessibility tree using axe describe-ui within shell loops in SKILL.md to find elements.
  • Boundary markers: None present. The agent processes the raw output of the UI tree.
  • Capability inventory: Full simulator interaction capabilities including tap, type, and record-video.
  • Sanitization: None detected. The skill uses grep to identify target elements by their raw labels.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 05:09 PM