The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses Python scripts to execute shell commands via subprocess.run to interact with Xcode development tools.\n
Evidence: scripts/benchmark_builds.py and scripts/diagnose_compilation.py invoke xcodebuild with various flags to perform builds, cleans, and timing analysis.\n
Implementation: Commands are constructed using list-based arguments which mitigates typical shell injection vulnerabilities, and the operations are core to the skill's primary purpose of build optimization.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from the local development environment that could potentially contain malicious instructions intended to influence the agent's behavior.\n
Ingestion points: scripts/benchmark_builds.py, scripts/diagnose_compilation.py, and scripts/generate_optimization_report.py read output from xcodebuild and content from Xcode project files (.xcodeproj, .pbxproj).\n
Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious content embedded in logs or project files.\n
Capability inventory: The skill has the ability to execute commands (xcodebuild), write files (artifacts and reports), and instruct the agent to modify project state after approval.\n
Sanitization: Data is processed via regular expression parsing to extract metrics, which provides some implicit filtering but does not fully sanitize the data against complex injection patterns.

xcode-build-orchestrator