looker-performance-optimizer
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses official vendor-provided tools (Looker CLI and Looker MCP) to interact with Looker projects and database connections. These interactions are consistent with the skill's primary purpose of performance optimization.
- [SAFE]: No obfuscation, data exfiltration, or hardcoded credentials were found in the skill files. All references to database connections and ETL metadata use generic placeholders or standard administrative table names.
- [SAFE]: The documentation includes example bash scripts for cache-warming workflows. These are provided as educational templates for developers and do not represent unauthorized or hidden command execution by the agent.
- [SAFE]: The skill defines a clear, multi-step workflow for query diagnostics that includes using subagents for parallel processing. This is an architectural optimization for agentic execution and does not bypass safety constraints.
- [SAFE]: Although the skill processes external data such as SQL execution plans and LookML files, it does so within a controlled developer environment to produce performance reports, and no indirect prompt injection vulnerabilities were identified in the logic.
Audit Metadata