The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a Python script (scripts/repo-doctor.py) that executes local git commands (such as rev-list and log) to gather repository statistics and history. These commands are executed via subprocess.run using argument lists without a shell, which prevents command injection vulnerabilities.
[DATA_EXFILTRATION]: The skill operates entirely on the local file system. It reads file contents and repository metadata for auditing purposes but contains no network-enabled code or exfiltration patterns.
[EXTERNAL_DOWNLOADS]: No external network requests, downloads, or remote script executions are present in the skill.
[PROMPT_INJECTION]: The instructions and reference documentation contain no patterns indicative of prompt injection or attempts to override AI safety guardrails.
[SAFE]: The skill's behavior aligns strictly with its documented purpose of providing repository health scores and remediation guidance. It includes comprehensive test suites and templates that follow secure development practices.

repo-doctor