software-ios-design

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted project source code, UI hierarchy snapshots, and simulator screenshots to perform design audits.
  • Ingestion points: Processes iOS project files and UI state data via XcodeBuildMCP integration during the design review loop described in SKILL.md and references/xcodebuildmcp-design-loop.md.
  • Boundary markers: The instructions do not provide explicit delimiters or instructions to ignore potential commands embedded in the audited project data.
  • Capability inventory: The agent uses shell-based scripts (build-ios.sh, run-ios.sh, test-ios.sh) to execute commands for building and running applications.
  • Sanitization: There is no evidence of sanitization or filtering applied to project content before it enters the agent's context.
  • [COMMAND_EXECUTION]: The skill includes several shell scripts (scripts/build-ios.sh, scripts/run-ios.sh, scripts/test-ios.sh, scripts/capture-screenshot.sh) that wrap calls to the xcodebuildmcp utility, enabling the agent to execute build, run, and diagnostic commands within the development environment.
  • [EXTERNAL_DOWNLOADS]: The scripts/_xcodebuildmcp_common.sh file uses npx -y xcodebuildmcp@latest to dynamically fetch and execute the xcodebuildmcp tool. This tool is an official utility provided by Sentry, which is a well-known and reputable service provider in the developer tools ecosystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 02:03 PM