The Agent Skills Directory

[SAFE]: The skill's logic is purely instructional and provides a framework for an AI agent to perform code reviews. It does not trigger any subprocesses, file system modifications, or network activity.
[NO_CODE]: No scripts (Python, JavaScript, etc.) or binary files are included with this skill, eliminating the risk of direct remote code execution or malware.
[PROMPT_INJECTION]: The skill expects to process external data in the form of pull request diffs. Although this is an untrusted data source, the skill possesses no capabilities (such as code evaluation or API access) that could be exploited through indirect prompt injection to harm the system or exfiltrate data.

pr-reviewer