sqlserver-expert

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Data Exposure & Exfiltration] (SAFE): The skill correctly uses environment variables (e.g., process.env.SQL_USER) rather than hardcoding credentials in the configuration examples.
  • [Prompt Injection] (SAFE): No instructions attempting to override agent behavior or bypass safety filters were identified.
  • [Remote Code Execution] (SAFE): No patterns of downloading or executing remote scripts were detected.
  • [Command Execution] (SAFE): The skill contains SQL and TypeScript snippets but does not invoke system-level commands or shell processes.
  • [Indirect Prompt Injection] (SAFE): While the skill provides templates for database interaction, it explicitly recommends using parameterized queries to prevent SQL injection at the application level.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:07 PM