The Agent Skills Directory

[SAFE]: The skill's primary function is to perform code analysis using legitimate system tools and local file access without any detected malicious intent.
[COMMAND_EXECUTION]: Executes standard git commands such as git diff, git log, and git rev-parse to retrieve changes and commit history for review. These commands are necessary for the skill's stated purpose and operate on the local repository.
[DATA_EXPOSURE]: Reads local project files, including coding standards (CODING_STANDARDS.md), contribution guidelines, and requirement specifications, to inform the review process. No sensitive system files or credentials are accessed.
[PROMPT_INJECTION]: Processes commit messages and code diffs which originate from users or external contributors. While this represents an ingestion point for untrusted data (Indirect Prompt Injection surface), it is inherent to the tool's function as a code reviewer and the skill does not exhibit any patterns of unsafe handling.

code-review