alloydb-omni-data
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The scripts use
npxto download and execute the@toolbox-sdk/serverpackage (version 1.1.0) from the npm registry. - [COMMAND_EXECUTION]: Database operations are performed by spawning sub-processes to invoke the toolbox server. The implementation includes platform-specific logic for command invocation and argument escaping on Windows and Linux.
- [PROMPT_INJECTION]: The skill processes untrusted database content, which creates a surface for indirect prompt injection.
- Ingestion points: SQL query results and database schema metadata returned by all scripts.
- Boundary markers: Absent; database output is processed and returned directly to the agent.
- Capability inventory: Shell command execution via
npxis available across all script files. - Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the database.
Audit Metadata