The Agent Skills Directory

[SAFE]: The skill consists exclusively of markdown-based guidelines and checklists for code review. It does not include any executable scripts, shell commands, or network-enabled operations.
[SAFE]: No sensitive data access, credential harvesting, or prompt injection patterns were found. The skill actually encourages security best practices by instructing the agent to look for hardcoded secrets and SQL injection vulnerabilities during reviews.
[SAFE]: The skill does not possess any capabilities (like file writing or command execution) that could be exploited via indirect prompt injection when processing untrusted code diffs.

code-review