The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell-based Git commands to perform repository operations. It adheres to security best practices by distinguishing between low-risk operations (e.g., status, fetch) and high-risk operations (e.g., force pushing, branch deletion), the latter of which require explicit user confirmation before execution.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. Ingestion points: Untrusted data from the repository is read via git log, git status, and git diff as described in SKILL.md. Boundary markers: No delimiters are defined to separate repository content from agent instructions. Capability inventory: The skill has the capability to write to the repository and push changes to remote servers via git commit and git push. Sanitization: The skill does not perform sanitization or escaping of the data ingested from the repository content.

branch-management