pg-messaging
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely informational, providing SQL schema definitions and queries for database-backed messaging. It does not contain any scripts, commands, or automation that would execute on the host system.
- [COMMAND_EXECUTION]: No shell commands or system-level execution patterns were detected. The SQL code provided is for database implementation and uses standard parameterized inputs ($1, $2, etc.) which follow security best practices.
- [EXTERNAL_DOWNLOADS]: The skill mentions common tools like sqlc, PostgREST, and pgbouncer in an architectural context but does not attempt to download or install any software.
- [PROMPT_INJECTION]: No instructions were found that attempt to subvert agent behavior, bypass safety guardrails, or reveal system prompts.
Audit Metadata