supabase-sql

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE] (SAFE): The skill consists entirely of Markdown documentation and JSON configuration. No executable scripts (Python, JavaScript, or Shell) are included in the package.
  • [PROMPT_INJECTION] (SAFE): No instructions attempt to bypass safety filters, override system behavior, or extract sensitive internal prompts.
  • [DATA_EXFILTRATION] (SAFE): No network requests or access to sensitive local files (e.g., SSH keys, AWS credentials) were detected.
  • [EXTERNAL_DOWNLOADS] (SAFE): No patterns for downloading or executing remote code or packages are present.
  • [PRIVILEGE_ESCALATION] (SAFE): The skill suggests using 'SECURITY DEFINER' in PostgreSQL templates and 'TO service_role' in RLS policies. While these are high-privilege constructs in a database context, they are standard best practices for the intended Supabase backend use case and do not grant elevated permissions to the agent itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:10 PM