phoenix-cli

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx @arizeai/phoenix-cli, which involves downloading and executing the CLI tool directly from the npm registry.
  • [EXTERNAL_DOWNLOADS]: The px docs fetch command is documented for downloading Phoenix-specific documentation and integration guides from remote sources into the local .px/docs directory.
  • [PROMPT_INJECTION]: The skill provides functions to retrieve and process untrusted data from LLM traces, datasets, and prompts (e.g., px trace get, px dataset get, px prompt get). This content is ingested into the agent's context and may contain instructions that could trigger indirect prompt injection. No specific boundary markers or 'ignore' instructions are provided to mitigate this risk.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 01:41 AM