Skills
Navigate
skills/duyet/codex-claude-plugins/ios-debugger-agent/Gen Agent Trust Hub

ios-debugger-agent

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data originating from an iOS simulator, creating a surface for indirect instructions to influence the agent.
  • Ingestion points: application logs and UI descriptions/screenshots from the simulator.
  • Boundary markers: The instructions lack explicit delimiters or warnings to treat ingested log/UI data as untrusted.
  • Capability inventory: The agent has the ability to execute xcodebuild and xcrun commands, and interact with the simulator UI via XcodeBuildMCP.
  • Sanitization: No specific filtering or sanitization of logs or UI content is mentioned.
  • [COMMAND_EXECUTION]: The skill uses xcrun simctl and xcodebuild to manage simulators and build software, which involves executing shell commands in the local environment.
  • [EXTERNAL_DOWNLOADS]: The skill references the XcodeBuildMCP tools located in Sentry's official GitHub repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 10:12 AM