phoenix-evals
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a documentation and reference set for Arize Phoenix, a legitimate AI observability and evaluation platform. All identified dependencies are official Arize packages or established industry-standard libraries.
- [SAFE]: Code snippets demonstrate standard usage of the Phoenix SDKs for Python and TypeScript, including tracing, dataset management, and evaluation workflows.
- [SAFE]: Secret management guidance follows security best practices, recommending the use of environment variables for API keys.
- [SAFE]: Evaluation templates include boundary markers (XML tags) to separate instructions from external data, reducing the risk of indirect prompt injection.
Audit Metadata