distributed postgres

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands for cluster management and database interaction via a psql fallback mechanism. It leverages official vendor tools like the AWS CLI and psql, representing standard and expected administrative functionality.
  • [PROMPT_INJECTION]: The skill processes externally sourced SQL, which presents a surface for indirect prompt injection. To address this, it mandates the use of dsql_lint for validation and safe_query.build() for query construction, ensuring that all user-provided input is properly sanitized and validated before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 08:50 PM
Security Audit — agent-trust-hub — distributed postgres