code-review-expert
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No patterns of instruction overrides, safety filter bypasses, or persona-based jailbreaks were detected in the skill's instructions or metadata.
- [DATA_EXFILTRATION]: The skill analyzes local source code via git commands and search tools. No evidence of unauthorized network transmission or hardcoded credentials was found. The skill includes defensive instructions to detect secret leakage in the code being reviewed.
- [REMOTE_CODE_EXECUTION]: All operations utilize local system binaries for code analysis. There are no patterns involving the download and execution of remote scripts or unverified packages during runtime.
- [COMMAND_EXECUTION]: The skill uses standard CLI tools for code analysis such as git, grep, and ripgrep. It does not execute arbitrary shell commands or perform high-risk operations like privilege escalation or service modification.
- [SAFE]: The skill implements a review-first workflow where code changes are analyzed and presented to the user. No implementation of fixes occurs without explicit human-in-the-loop confirmation, providing a strong control against accidental or malicious modifications.
Audit Metadata