The Agent Skills Directory

[SAFE]: The skill consists entirely of high-quality instructional text designed to guide an AI agent through a structured code review process. No executable scripts, binaries, or configuration files are included.
[SAFE]: No external network requests, data exfiltration patterns, or hardcoded credentials were detected. The skill operates purely within the context of the data provided to it during a session.
[SAFE]: No prompt injection or bypass attempts were found. The instructions are focused on adherence to project plans and maintainability standards.
[SAFE]: The skill explicitly includes security analysis as part of its review process, directing the agent to check for hardcoded secrets, injection vectors (SQL, HTML, Shell), and improper authorization checks in implementation changes.
[SAFE]: No obfuscation, hidden characters, or suspicious encoding techniques were identified in the document content.

code-reviewer