gitlab-code-review
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No malicious instructions, safety bypasses, or attempts to override agent behavior were detected. The instructions provide constructive behavioral guidelines for performing code reviews.\n- [DATA_EXFILTRATION]: The skill interacts exclusively with a self-hosted GitLab instance (https://gitlab-erp-pas.dedalus.lan) belonging to the vendor. No data exfiltration to unauthorized external domains was identified.\n- [REMOTE_CODE_EXECUTION]: No patterns of remote code execution, piped shell commands, or dynamic code generation from untrusted sources were found.\n- [COMMAND_EXECUTION]: The skill uses a predefined set of tools through the gitlab-mcp server. No arbitrary shell command execution or unauthorized system access was detected.\n- [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or other sensitive credentials were found. The skill relies on externally configured access for the GitLab instance.
Audit Metadata