skills/better-auth/skills/create-auth/Gen Agent Trust Hub

create-auth

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill scans local project configuration files (like package.json and ORM configs) to automate implementation. While this is a standard feature for developer tools, it represents a potential ingestion surface for instructions embedded in local files.
  • Ingestion points: Reads local file system for package.json, ORM schemas, and framework configurations.
  • Boundary markers: None explicitly defined for file scanning.
  • Capability inventory: Generates shell commands, creates environment variables, and writes authentication configuration files.
  • Sanitization: Not explicitly present in the provided markdown instructions.
  • [EXTERNAL_DOWNLOADS]: References official documentation at better-auth.com and provides links to sample code on GitHub. These resources are controlled by the skill author.
  • [COMMAND_EXECUTION]: Provides standard shell commands for package installation and database management (e.g., npm install, npx prisma migrate). These are standard industry practices for project scaffolding.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 10:50 AM
Security Audit — agent-trust-hub — create-auth