auditing-endpoints

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the execute-sql tool to query internal system tables, specifically system.data_modeling_endpoints for metadata and query_log for usage statistics. This is the primary intended mechanism for auditing project resources.
  • [COMMAND_EXECUTION]: The skill includes access to the endpoint-update tool, which allows for modifying endpoint states (disabling or unmaterializing). Security risks are mitigated by explicit instructions requiring the agent to obtain human confirmation before executing any modification commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 10:58 AM
Security Audit — agent-trust-hub — auditing-endpoints