looker-architect

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script (looker_scaffold.py) and the Looker CLI (looker-cli) to automate LookML project initialization and validation. These operations are restricted to the local environment and the user's authenticated Looker session.
  • [EXTERNAL_DOWNLOADS]: The skill references and downloads tools from official and well-known sources, including the Looker CLI and the lkml Python parser. These are legitimate dependencies for the intended functionality.
  • [DATA_EXPOSURE]: The skill instructions and templates follow security best practices, such as recommending the use of GitHub Secrets for API credentials in CI/CD pipelines and utilizing OAuth for session management.
  • [PROMPT_INJECTION]: Instructions for the agent to 'Act as a Looker Architect' are task-specific role-play patterns and do not attempt to bypass safety filters or override core agent constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 07:18 AM
Security Audit — agent-trust-hub — looker-architect