better-auth-organization-best-practices

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the user to execute npx @better-auth/cli migrate to set up the necessary database tables (organization, member, invitation). This is a standard part of the library's setup process.
  • [INDIRECT_PROMPT_INJECTION]: The skill demonstrates an invitation system that interpolates user-controlled data into HTML email content, which could be exploited if the inputs are malicious.
  • Ingestion points: User and organization names are retrieved and used within the sendInvitationEmail hook in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions to the agent to treat this data as untrusted content within the provided code examples.
  • Capability inventory: The skill utilizes a sendEmail function to deliver the generated HTML content to external email addresses.
  • Sanitization: The provided code snippets use raw JavaScript template literals for HTML construction without demonstrating sanitization, escaping, or validation of the interpolated variables.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 11:03 PM
Security Audit — agent-trust-hub — better-auth-organization-best-practices