The Agent Skills Directory

[SAFE]: The skill utilizes official Arize resources, including the arize-ax-cli and the arize Python SDK, to manage annotation configurations and queues.
[SAFE]: Security best practices are followed for credential management; the skill instructs users to use environment variables for API keys and explicitly warns against disclosing secrets in chat or accessing sensitive local files.
[INDIRECT_PROMPT_INJECTION]: The skill handles data from external sources such as spans and dataset records. While this represents a potential injection surface, the risk is mitigated by the use of structured data schemas and the limitation of actions to annotation metadata updates, without performing arbitrary code execution or network requests based on the ingested content.

arize-annotation