tanstack-start-auth

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The instructions specify using bunx @better-auth/cli for managing database migrations and generating schemas, which is standard operational practice for the Better Auth library.- [INDIRECT_PROMPT_INJECTION]: The skill manages external data such as request headers and callback URLs as part of its authentication logic.
  • Ingestion points: request.headers and callbackURL search parameters are processed in SKILL.md and references/auth.md.
  • Boundary markers: The skill mandates the use of route-level beforeLoad redirects and endpointAuth session guards for all data boundaries.
  • Capability inventory: The skill involves database persistence via adapters and HTTP redirects for auth flows.
  • Sanitization: Includes specific instructions to block dangerous callbackURL prefixes to prevent open redirect vulnerabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 04:42 PM