The Agent Skills Directory

[SAFE]: No security issues detected. The skill follows secure development practices for AI agents.
[SAFE]: The skill includes explicit instructions for the agent to redact credentials from Git remote URLs (e.g., replacing 'user:token@' with '***@') before displaying them to the user, preventing sensitive data exposure.
[SAFE]: The included helper script scripts/sync_fork.py relies exclusively on the Python standard library and does not download or execute external code. It interacts with the Git CLI using subprocess.run without a shell, which prevents command injection vulnerabilities.
[SAFE]: All significant operations, especially destructive ones like git reset --hard or git push --force-with-lease, are designed with human-in-the-loop safeguards, requiring the agent to present a plan and obtain explicit user confirmation before proceeding.

sync-fork