The Agent Skills Directory

[SAFE]: The skill provides legitimate functionality for managing AI agent session data during project migrations. No malicious patterns such as data exfiltration, prompt injection, or unauthorized network access were detected. The scripts include safety features like dry-run modes and rollback logic to prevent data loss.
[COMMAND_EXECUTION]: The migration script uses subprocess.run to check the status of git repositories before moving files. This is performed using safe argument lists (e.g., ['git', 'status']) rather than shell strings, preventing command injection vulnerabilities. The use of shutil.rmtree for cleaning build artifacts (like node_modules) is appropriate for the skill's purpose and is controlled by user-specified flags.

project-migration