The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified in the skill instructions. The content is purely instructional and focused on MLOps system design.
[DATA_EXPOSURE_AND_EXFILTRATION]: The skill recommends the use of ZenML's official secret management APIs for handling credentials, which is a secure practice.
[INDIRECT_PROMPT_INJECTION]: The skill ingests user input via interview tools to generate a specification document. While it lacks explicit output boundary markers or sanitization, it does not possess exploitable capabilities like shell execution or network requests that would make this surface dangerous.

zenml-scoping