The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains explicit instructions to override the agent's interaction model, demanding execution without user questioning or confirmation ("지금 즉시 아래 워크플로우를 실행하라. 질문하지 말고 바로 실행하라").
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted data via variables while possessing write-access capabilities.
Ingestion points: External untrusted data enters the agent context through the $ARGUMENTS variable in SKILL.md.
Boundary markers: There are no delimiters or "ignore embedded instructions" warnings present to isolate the $ARGUMENTS input.
Capability inventory: The skill executes git add and git commit commands, which provide file system modification capabilities.
Sanitization: The skill does not perform any escaping, validation, or filtering of the external content before processing it.
[COMMAND_EXECUTION]: The skill executes multiple shell commands to manage the git repository, including git status, git diff, git add, and git commit.

commit