The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands to interact with Git. It runs git config user.name and git config user.email to identify the author, and git log to retrieve commit messages within a specified timeframe. These are standard operations for the skill's purpose.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes Git commit messages, which are external strings. If a commit message contained instructions designed to manipulate the AI, the agent might interpret them. However, the skill includes structured output contracts and categorization rules which provide a level of implicit boundary for the processing logic.

yy-create-report