The Agent Skills Directory

[SAFE]: The skill implements automated auditing and remediation of Android project files using local Python scripts.
[COMMAND_EXECUTION]: The script scripts/generate_remediation_checklist.py uses subprocess.run() to execute a secondary script (scan_project.py). This is a safe implementation as it passes arguments as a list and avoids shell execution (shell=False), preventing command injection.
[DATA_EXFILTRATION]: No network operations, external API calls, or data exfiltration patterns (such as curl, wget, or requests) were detected. All analysis is performed locally on the provided project path.
[PROMPT_INJECTION]: The skill's instructions and metadata focus on technical Android modernization tasks and do not contain patterns attempting to bypass agent safety filters or override system instructions.
[DYNAMIC_EXECUTION]: The code uses standard library modules like re, pathlib, json, and struct to process files. It does not use eval() or exec() for dynamic code evaluation.
[SAFE]: The automated file modifications performed by scripts/apply_safe_upgrades.py are deterministic, replacing known legacy patterns (e.g., jcenter(), android.support) with modern equivalents based on Google's official migration guides.

android-modernization-upgrade