The Agent Skills Directory

[SAFE]: The skill follows security best practices for AI agents by explicitly instructing the model to treat processed data (PR descriptions, commit messages, and file changes) as context rather than instructions. This directly addresses the risk of indirect prompt injection.
[COMMAND_EXECUTION]: The skill uses git and gh (GitHub CLI) for repository inspection. These commands are restricted to read-only operations unless the user explicitly requests otherwise, minimizing the risk of accidental or malicious modification of the local environment.
[DATA_EXFILTRATION]: No unauthorized network operations or data exfiltration patterns were detected. Network access via the GitHub CLI is consistent with the skill's stated purpose of reviewing pull requests.

review-pr