mz-commit
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local scripts such as bin/fmt and bin/lint, as well as standard development tools like cargo and git. These commands are integral to the project's development workflow and do not involve untrusted remote sources.
- [DATA_EXFILTRATION]: No network activity or unauthorized access to sensitive data was detected. The skill interacts only with local repository files for formatting and commit preparation.
- [PROMPT_INJECTION]: No patterns associated with prompt injection or safety bypass were found in the skill instructions or metadata.
Audit Metadata