skills/growth4u-sytems/gattaca-secuenciador-de-prompts/supabase-postgres-best-practices/Gen Agent Trust Hub
supabase-postgres-best-practices
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [Metadata Poisoning] (SAFE): The author field identifies 'supabase', which is a recognized trusted organization.
- [No Code] (SAFE): The skill consists exclusively of markdown documentation and references to other markdown files; no code execution or command triggers are present.
- [Indirect Prompt Injection] (LOW): The skill is designed to evaluate user-provided SQL queries, which constitutes an untrusted data ingestion surface. Ingestion points: User-provided SQL schemas and queries. Boundary markers: Absent. Capability inventory: No executable capabilities or external access (Documentation only). Sanitization: Absent. The impact is limited to agent reasoning, posing no system-level risk.
Audit Metadata