limrun-ios-simulator

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the lim CLI tool via NPM (npm install --global lim). This is a vendor-provided tool from limrun-inc required for managing their cloud-hosted iOS simulator infrastructure.
  • [COMMAND_EXECUTION]: The skill executes various lim CLI subcommands (e.g., lim ios create, lim ios tap, lim ios launch-app) to manage and drive the iOS simulator. These are standard operations for UI automation and testing within the vendor's ecosystem.
  • [PROMPT_INJECTION]: The skill processes data from the iOS accessibility tree via lim ios element-tree, which presents an indirect prompt injection surface (Category 8c). Maliciously crafted labels in a tested app could attempt to influence agent behavior.
  • Ingestion points: The agent reads UI hierarchy and labels from the output of the element-tree command.
  • Boundary markers: No delimiters are specified to distinguish between UI data and instructions.
  • Capability inventory: The agent can execute simulator control commands and perform filesystem writes for screenshots.
  • Sanitization: No sanitization of the application's UI strings is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 08:14 AM
Security Audit — agent-trust-hub — limrun-ios-simulator