skills/bjesuiter/skills/xcode/Gen Agent Trust Hub

xcode

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes bunx to execute mcporter and xcodebuildmcp. While bunx may download packages from the npm registry if not present locally, these resources are integral to the skill's operation and are associated with the author's own development tools.\n- [COMMAND_EXECUTION]: Interfaces with system-level development utilities through the mcporter bridge, enabling the agent to perform extensive automation of build and test workflows as part of its primary function.\n- [DYNAMIC_EXECUTION]: The skill is designed to compile and run software for Apple platforms using xcodebuild. This functionality is necessary for developing and testing iOS/macOS applications.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external environments, including Xcode project files, simulator logs, and UI view hierarchies. This creates a surface where the agent might encounter untrusted content embedded in those sources.\n
  • Ingestion points: Project configuration files (.xcodeproj, .xcworkspace), simulator logs, and UI accessibility data retrieved via the describe_ui tool.\n
  • Boundary markers: There are no explicit delimiters or specific instructions for the agent to ignore embedded commands in the processed data.\n
  • Capability inventory: The skill possesses significant capabilities, including code compilation, filesystem discovery, and UI automation (tap, type, and gestures).\n
  • Sanitization: Relies on the security controls of the host operating system and the agent's internal safety guardrails to mitigate risks from ingested content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 05:25 AM