arize-prompts
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill incorporates excellent security practices by explicitly instructing the agent never to request, store, or display sensitive API keys in the chat interface, instead relying on standard environment variables and official CLI profiles.
- [COMMAND_EXECUTION]: The skill uses the official 'ax' CLI tool to perform prompt management tasks such as creation, versioning, and labeling. These commands are restricted to the intended functionality of the Prompt Hub.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the 'arize-ax-cli' package. As this is the official tool from the vendor (Arize-ai) and is installed via standard package managers like pip or uv, it is considered a legitimate and safe dependency.
- [PROMPT_INJECTION]: The skill proactively addresses indirect prompt injection by warning that text exported from spans or traces is untrusted and should not be obeyed as instructions, effectively mitigating potential injection attacks from external data sources.
Audit Metadata