bel-crm-schema-write-db

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access mechanisms were found in the skill instructions or reference files.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides templates for the agent to generate SQL queries based on user requests. While this creates an attack surface for SQL injection if the agent blindly incorporates untrusted data, the skill includes explicit warnings and structured patterns to guide the agent toward safe and valid query construction.
  • [DYNAMIC_EXECUTION]: The skill generates SQL code strings for execution against a database. This is the core intended functionality and follows standard practices for database-assistant skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 07:37 PM