mirrord-db-branching
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Prompt Injection] (LOW): Detected a surface for indirect prompt injection (Category 8).
- Ingestion points: User instructions for generating mirrord configurations (e.g., 'Set up a MySQL database branch') as described in README.md.
- Boundary markers: Absent in the documentation and configuration templates.
- Capability inventory: The skill suggests using the mirrord CLI, which has the capability to execute commands in remote containers and inspect environment variables containing sensitive information (e.g., 'mirrord exec' in references/troubleshooting.md).
- Sanitization: No specific sanitization or validation of the user-provided parameters is described in the reference files. This vulnerability surface is typical for skills designed to facilitate CLI tool configuration.
Audit Metadata