postgres

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill is entirely composed of documentation and instructional content. No evidence of obfuscation, credential theft, or unauthorized persistence was found.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and configuration guidelines hosted on the author's official GitHub repository at github.com/planetscale/database-skills.
  • [COMMAND_EXECUTION]: Provides guidance on using standard database management tools such as psql, pg_dump, and the PlanetScale CLI (pscale) for administrative operations.
  • [PROMPT_INJECTION]: While the skill mentions an MCP server for executing queries, it does not include instructions designed to bypass agent safety filters or override core behaviors.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 09:20 PM