neon-postgres

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches documentation from Neon's official website (neon.com) and GitHub repository (github.com/neondatabase). These are official resources for the service.- [COMMAND_EXECUTION]: Provides instructions to run npx, npm, and pip commands to initialize tools like the Neon CLI, MCP server, and various SDKs.- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external documentation content.
  • Ingestion points: Documentation pages fetched from neon.com.
  • Boundary markers: Includes instructions to treat fetched docs as the source of truth and verify against them.
  • Capability inventory: Execution of shell commands (npx, npm) and environment variable management.
  • Sanitization: Does not implement explicit sanitization for the markdown data fetched from the web.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 11:40 PM
Security Audit — agent-trust-hub — neon-postgres