The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected. The skill instructions prioritize secure handling of API keys by using environment variables and avoiding direct disclosure in communication channels.
[EXTERNAL_DOWNLOADS]: The skill references the official 'arize-ax-cli' and Python 'arize' packages, which are legitimate tools provided by the vendor for interacting with their service.
[PROMPT_INJECTION]: While the skill handles external data inputs for annotation, which is a common surface for indirect prompt injection, this is a functional requirement of the skill and no exploitable injection vulnerabilities were found.

arize-annotation