The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions include a workflow step that executes a local Python script (scripts/diagnose_compilation.py) with several command-line arguments. Because this script file was not included in the provided skill files, its logic and safety cannot be verified. This represents a risk as the script could perform unauthorized file system or network operations.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external, potentially untrusted data such as Xcode build logs, timing summaries, and compiler diagnostic files.\n
Ingestion points: Processes Build Timing Summary output, CompileSwiftSources logs, and JSON statistics from the -stats-output-dir flag (found in SKILL.md and references/code-compilation-checks.md).\n
Capability inventory: The agent has the capability to execute shell commands (via the Python script) and read project-related files (SKILL.md).\n
Boundary markers: The instructions lack explicit boundary markers or directions for the agent to ignore instructions embedded within the build data.\n
Sanitization: There is no evidence of input validation or sanitization for the build logs before they are parsed for analysis.

xcode-compilation-analyzer