backend-db-performance
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a structured methodology for identifying and resolving database performance bottlenecks using standard tools.
- [COMMAND_EXECUTION]: The instructions direct the agent to check local migration files using
lsandgrep. This is a legitimate development practice to prevent redundant index creation and ensure schema consistency. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for untrusted data (slow queries and database logs). However, it mitigates risk through a structured reasoning loop and mandatory verification via
EXPLAIN ANALYZE. Capability inventory includes SQL execution and filesystem metadata reads; boundary markers are established via worked examples. - [EXTERNAL_DOWNLOADS]: The skill references established libraries like
@prisma/clientand Supabase services, which are standard infrastructure for the skill's specific technical domain.
Audit Metadata