Skills
skills/gaelic-ghost/apple-dev-skills/apple-xcode-workflow/Gen Agent Trust Hub

apple-xcode-workflow

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes internal helper scripts and generates command strings for development workflows.
  • Evidence: scripts/run_workflow.py invokes bash and python helpers to detect Xcode project scopes and check advisory cooldowns. It also constructs xcodebuild and swift command strings as fallback execution paths.
  • [EXTERNAL_DOWNLOADS]: The documentation references external repositories for skill installation and discovery.
  • Evidence: references/skills-installation.md and references/skills-discovery.md link to the author's GitHub repository and the well-known vercel-labs/agent-skills repository.
  • [PROMPT_INJECTION]: The skill ingests workspace data and user input, creating a surface for indirect prompt injection.
  • Ingestion points: The workspace_path input and workspace file contents such as Package.swift.
  • Boundary markers: No explicit delimiters are used to isolate processed workspace data from agent instructions.
  • Capability inventory: Local script execution via subprocess.run, file system reads, and CLI command generation.
  • Sanitization: shlex.quote is used to sanitize data used in constructed fallback command strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 09:37 PM