supabase

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a reference guide for developers and does not contain any malicious instructions, prompt injections, or obfuscated code. It is marked with disable-model-invocation: true, indicating it is intended for context/documentation rather than direct execution by the agent.
  • [EXTERNAL_DOWNLOADS]: The instructions include installing standard, well-known packages from the official npm registry (@supabase/supabase-js, supabase, @supabase/ssr) and referencing modules from established repositories like deno.land and esm.sh for Edge Functions.
  • [CREDENTIALS_UNSAFE]: The skill correctly demonstrates using environment variables for secret management and explicitly warns against exposing the service_role key in client-side code, adhering to security best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 04:19 PM
Security Audit — agent-trust-hub — supabase