skills/arize-ai/phoenix/phoenix-cli/Gen Agent Trust Hub

phoenix-cli

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the official @arizeai/phoenix-cli package from the npm registry using npx.
  • [REMOTE_CODE_EXECUTION]: Runs the vendor's command-line interface directly via npx for debugging and tracing tasks.
  • [COMMAND_EXECUTION]: Uses the px CLI and jq to query, filter, and display LLM application data.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from LLM traces and prompts which could contain malicious instructions. Ingestion points: Trace data, dataset examples, and prompts fetched via px traces, px dataset, and px prompt. Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are present. Capability inventory: Execution of CLI commands and GraphQL API queries. Sanitization: No explicit validation or sanitization of external LLM content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 08:48 PM