text-to-sql

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, prompt injections, or data exfiltration attempts were identified in the skill instructions or scripts.
  • [SAFE]: The skill incorporates robust defensive instructions ('Iron Laws') that mandate parameterized queries and schema validation, specifically designed to prevent SQL injection vulnerabilities.
  • [EXTERNAL_DOWNLOADS]: The documentation mentions promptfoo, which is a well-known and widely used industry tool for evaluating LLM prompts and outputs. Its reference in the context of skill evaluation is standard developer practice.
  • [COMMAND_EXECUTION]: Shell scripts provided for pre- and post-execution hooks are limited to basic input validation and project directory traversal using standard Node.js APIs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 01:17 PM