The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions direct the agent to execute a series of shell commands using the git binary to inspect repository status, fetch remote data, and create commits (e.g., git diff, git fetch origin, git commit). These operations are necessary for the skill's purpose but represent active command execution within the agent's environment.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to ingest and process potentially untrusted data from external sources.
Ingestion points: Untrusted content enters the agent's context through the output of git diff and git status, as well as via task requirements retrieved from issue trackers (e.g., GitHub Issues or Jira).
Boundary markers: The instructions provide a rigid structure for the output (conventional commit format) but do not explicitly instruct the agent to use delimiters or ignore instructions that might be embedded within code comments in a diff or within issue descriptions.
Capability inventory: The skill has the capability to write to the repository (via git commit), create new branches (git branch), and perform network operations to synchronize with remote repositories (git fetch).
Sanitization: There are no specific instructions for the agent to sanitize or filter the ingested data before using it to generate the commit message body.

commit-creator