The Agent Skills Directory

[SAFE]: The skill's primary function is to perform technical code reviews. All instructions and reference materials are professional, well-documented, and aligned with the stated purpose of improving code quality and security.
[SAFE]: The tool configuration is limited to safe file-system operations (Read, Grep, Glob) and does not include network access or capabilities for executing external code.
[SAFE]: The skill handles untrusted data (external code and PR descriptions) as part of its core workflow. While this is an attack surface for indirect prompt injection, the skill's instructions require the agent to maintain a specific reviewer persona and summarize intent, which serves as a procedural safeguard against malicious data influencing the agent's behavior.
[SAFE]: No evidence of obfuscation, credential exfiltration, persistence mechanisms, or unauthorized privilege escalation was found in any of the skill's files.

code-reviewer