The Agent Skills Directory

[PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from the Kubernetes cluster environment, creating a surface for indirect prompt injection.
Ingestion points: The skill utilizes kubectl logs, kubectl describe pod, and kubectl get events to retrieve information from the cluster (SKILL.md).
Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potential malicious content within cluster outputs.
Capability inventory: The skill has access to the Bash tool and file system operations (Read, Write, Edit, Glob, Grep) as defined in the frontmatter.
Sanitization: No sanitization or filtering of the retrieved cluster data is implemented.
[COMMAND_EXECUTION]: The skill provides instructions and examples for executing commands within the cluster environment.
Evidence: Documentation includes kubectl exec -it <pod> -n agents -- /bin/sh, which allows for interactive shell access to containers (SKILL.md).

kubernetes