database-backup
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows established security principles for database administration. It explicitly instructs the agent to avoid hardcoding secrets, suggests the use of secret managers, and includes safety checks before performing destructive operations like database restores.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied database configurations which are interpolated into executable shell scripts. This is a vulnerability surface inherent to the tool's primary purpose and is mitigated by the skill's safety instructions.
- Ingestion points: Database type, name, and connection details provided in the usage phase (SKILL.md).
- Boundary markers: The skill includes a 'Safety and Permissions' section requiring explicit user authorization and verification of targets before execution.
- Capability inventory: The generated scripts utilize database CLI tools (pg_dump, mongodump), file system operations (mkdir, tar), and deletion commands (find -delete, rm) for retention management.
- Sanitization: The skill recommends secret-manager injection and environment variables instead of hardcoded credentials to prevent exposure.
Audit Metadata