arize-dataset

Pass

Audited by Gen Agent Trust Hub on May 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the ax CLI to perform dataset operations including listing, creating, and appending examples as part of its core functionality.
  • [EXTERNAL_DOWNLOADS]: The documentation references the installation of the arize-ax-cli package via standard, well-known package managers such as pip, uv, and pipx.
  • [DATA_EXFILTRATION]: The skill includes commands to export dataset content from the Arize platform to the local filesystem for offline analysis.
  • [PROMPT_INJECTION]: The instructions include a behavioral override for the agent to skip proactive version and environment checks to optimize performance, and prompts to offer credential persistence at the end of a session.
  • [SAFE]: The skill contains explicit security guidelines that prohibit the agent from searching the local filesystem for credentials or reading .env files, emphasizing the use of environment variables for secret management.
Audit Metadata
Risk Level
SAFE
Analyzed
May 26, 2026, 10:07 AM
Security Audit — agent-trust-hub — arize-dataset