neon-postgres

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to fetch and install additional agent skills from the official neondatabase/agent-skills repository using the npx skills add command. These are official resources from the skill vendor.
  • [COMMAND_EXECUTION]: Instructs the agent on how to use the Neon CLI for environment management (neon env pull) and database diagnostics (neon inspect db).
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the use of database exploration tools like run_sql and inspect_database which process user-directed input.
  • Ingestion points: User parameters provided to CLI/MCP tools and custom SQL statements for performance analysis as described in SKILL.md.
  • Boundary markers: The instructions include a dedicated section on interpreting results safely and explicit warnings to avoid running mutating SQL autonomously.
  • Capability inventory: Utilizes Neon CLI tools and MCP server functions for database inspection and query execution across the skill files.
  • Sanitization: Recommends using predefined diagnostic checks (table-sizes, outliers, etc.) instead of manual catalog queries and emphasizes safe execution of ANALYZE commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 08:51 AM
Security Audit — agent-trust-hub — neon-postgres