better-auth

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONNO_CODE
Full Analysis
  • EXTERNAL_DOWNLOADS (MEDIUM): The skill requires the installation of the better-auth and @better-auth/cli packages via npm. As these do not originate from the defined list of trusted organizations, they are classified as unverifiable dependencies.
  • COMMAND_EXECUTION (LOW): The documentation includes instructions to execute CLI tools using npx for managing database schemas, which involves running external code.
  • NO_CODE (LOW): The main SKILL.md file references an initialization script at scripts/better_auth_init.py that was not included in the provided files, preventing a full security audit of its functional logic.
  • CREDENTIALS_UNSAFE (SAFE): Documentation examples use placeholders for sensitive environment variables like BETTER_AUTH_SECRET and OAuth secrets.
  • PROMPT_INJECTION (SAFE): No malicious instructions or safety filter bypass attempts were detected in the skill files.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:27 PM