xcode-build-orchestrator

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes multiple shell commands and local Python scripts, including xcodebuild for project compilation, git log and git ls-remote for version control analysis, and specialized Python scripts (benchmark_builds.py, diagnose_compilation.py, generate_optimization_report.py) for benchmarking and report generation.\n- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting untrusted data from external sources.\n
  • Ingestion points: xcodebuild stdout/stderr, git log output, and content from referenced SKILL.md files in sibling directories.\n
  • Boundary markers: The skill generates structured reports using a template, but does not explicitly mention sanitization of log content or instructions to ignore embedded commands.\n
  • Capability inventory: The skill has capabilities to execute shell commands (python3, xcodebuild, git) and modify files (delegated to xcode-build-fixer in Phase 2).\n
  • Sanitization: No explicit sanitization or filtering of external log content is documented.\n- [DYNAMIC_EXECUTION]: The skill relies on executing local Python scripts at runtime to perform its core functions. These scripts are invoked via python3 with arguments derived from the project environment, representing a standard but noteworthy dynamic execution pattern.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 02:32 PM