The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute standard Git commands like git status and git commit to manage project changes.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it processes untrusted file names from the repository to generate messages and commands. * Ingestion points: Modified file names are read via git status --short in SKILL.md. * Boundary markers: None; there are no delimiters to isolate file names from the command structure. * Capability inventory: Includes the ability to execute git commit via the shell. * Sanitization: None specified; the skill does not instruct the agent to escape file names before use.
[SAFE]: No malicious patterns, such as data exfiltration, credential harvesting, or unauthorized remote downloads, were detected in the skill instructions.

git-commit