The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses git and gh CLI tools to perform repository operations such as staging changes, committing, and opening pull requests.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it incorporates external data from source code diffs and user arguments into its logic.
Ingestion points: The skill reads data from git status, git diff, and $ARGUMENTS.
Boundary markers: No delimiters or safety instructions are used to distinguish between repo data and system instructions.
Capability inventory: The skill can execute commands to modify the repository and create PRs.
Sanitization: Input data is not sanitized or escaped before being processed by the agent.

gh-ship