code-review-standards
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is entirely non-executable, consisting of Markdown guidance and JSON metadata. It does not provide any scripts, binary files, or tool-calling capabilities.
- [SAFE]: Automated scanner flags for 'eval' and 'exec' in
references/criteria-critical.mdare confirmed false positives. These terms appear as descriptive criteria in a checklist to help a code-review agent identify issues in target code; they are not part of any functional code within the skill itself. - [SAFE]: Hardcoded secret patterns (e.g., 'sk-', 'AWS') and placeholder credentials (e.g., 'hunter2') identified in the criteria files are used strictly as examples for detection training and do not constitute actual leaks or vulnerabilities.
- [SAFE]: The skill configuration in
SKILL.mdexplicitly disables model invocation and restricts user invocation, ensuring it remains a static reference for agent-to-agent workflows. - [SAFE]: No unauthorized network communication or exfiltration paths were identified. All external references are plain-text documentation links to the author's repository or legitimate third-party documentation services.
Audit Metadata