The Agent Skills Directory

[SAFE]: The skill uses dynamic context injection (!command syntax) to gather environment details such as repository remotes, default branch configuration, and authentication status. These are benign operations used to populate the agent's context for GitHub operations.
[SAFE]: File content is read and processed using the base64 tool to facilitate GitHub API interactions. This is a functional requirement for the Git-over-API workflow and does not constitute malicious obfuscation.
[SAFE]: The skill demonstrates security awareness by instructing the agent to write PR body content to a temporary file before passing it to the GitHub CLI. This practice effectively prevents shell command injection that could arise from processing untrusted text in a command-line argument.

git-api-pr