neon-auth

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves reference documentation, code generation rules, and troubleshooting guides from the neondatabase-labs GitHub repository. These resources provide the agent with official implementation patterns and best practices for the Neon Auth service.
  • [INDIRECT_PROMPT_INJECTION]: The skill performs environment detection to determine the project framework and configuration.
  • Ingestion points: The agent reads files including package.json, tailwind.config.js, .env.local, and the file system structure via guides/nextjs-setup.md.
  • Boundary markers: The skill does not employ explicit delimiters for project data, relying on its internal procedural logic.
  • Capability inventory: The skill utilizes bash for command execution and write for creating configuration files.
  • Sanitization: Data from ingested files is used for branching logic and presence checks rather than being directly executed or interpolated into sensitive paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 04:56 PM
Security Audit — agent-trust-hub — neon-auth