ce-test-xcode

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing xcodebuildmcp using brew tap getsentry/xcodebuildmcp or npx xcodebuildmcp. These resources originate from Sentry, a well-known technology provider.
  • [COMMAND_EXECUTION]: The skill performs project discovery, builds simulator apps, manages simulator states (boot/shutdown), and installs/launches applications. It also uses xcrun simctl openurl as a fallback mechanism for interacting with SwiftUI links.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes simulator logs to detect crashes, exceptions, and network errors, which represents a potential surface for indirect instructions hidden in application output.
  • Ingestion points: Application logs and console errors are captured in references/test-and-report.md.
  • Boundary markers: The instructions do not specify explicit delimiters or "ignore" instructions for the log content.
  • Capability inventory: The agent has capabilities to build, install, and launch apps, as well as invoke separate debugging skills (ce-debug).
  • Sanitization: There is no mention of filtering or sanitizing log data before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 05:30 AM
Security Audit — agent-trust-hub — ce-test-xcode