motherduck-ducklake

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely instructional, providing decision-making frameworks and SQL code snippets for MotherDuck storage management. It does not perform any autonomous actions, file system modifications, or network requests.
  • [DATA_EXFILTRATION]: No evidence of sensitive data access or unauthorized exfiltration. SQL examples use generic placeholders (e.g., 's3://my-bucket/'), and the documented 'ATTACH' protocol ('ducklake:md:...') is a standard feature of the MotherDuck platform provided by the vendor.
  • [REMOTE_CODE_EXECUTION]: The skill does not include any remote script downloads, package installations, or dynamic execution patterns that could lead to unauthorized code execution.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 06:31 PM