sqlserver-expert

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [CREDENTIALS_UNSAFE] (SAFE): The provided Node.js code snippets utilize environment variables for database credentials, avoiding the risk of hardcoded secrets.
  • [PROMPT_INJECTION] (SAFE): No malicious instruction overrides, jailbreak attempts, or system prompt extraction patterns were identified in the metadata or instructions.
  • [COMMAND_EXECUTION] (SAFE): There are no indicators of system-level command execution or shell spawning.
  • [DATA_EXFILTRATION] (SAFE): The skill does not attempt to access sensitive system files or exfiltrate data to external domains.
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill references the legitimate 'mssql' package but does not perform any unauthorized downloads or remote script executions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:39 PM