supabase-performance-tuning

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process results from Supabase API calls. This creates a potential surface where adversarial instructions in the database content could attempt to influence agent behavior.
  • Ingestion points: Data retrieved from Supabase is processed in cachedSupabaseRequest and cachedWithRedis (references/caching-strategy.md).
  • Boundary markers: No specific delimiters or safety instructions are defined for the handled data.
  • Capability inventory: The skill utilizes Read, Write, and Edit tools (SKILL.md), increasing the potential impact of an injection.
  • Sanitization: The provided examples show standard data fetching and caching logic without explicit validation or sanitization for injected instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 07:17 AM