The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on executing local system commands to perform its core function.
Evidence: The instructions direct the agent to use git status, git diff, cat, and sed to inspect the repository and read file content for summarization.
[PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes untrusted file content.
Ingestion points: File data is read into the context via cat and git diff as specified in SKILL.md.
Boundary markers: The prompt lacks delimiters or specific instructions to the agent to treat file content as data only and ignore embedded instructions.
Capability inventory: The skill has the capability to read file contents and execute git commands.
Sanitization: No content filtering or sanitization is performed on the data retrieved from the files before it is processed by the model.

git-committer