sap-kyma-cli
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines a set of commands for building container images with
podmanand managing Kubernetes resources withkubectl. These operations are standard for deployment workflows and are consistent with the skill's purpose. - [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow that involves reading and applying local Kubernetes manifests and environment files. This creates a surface for indirect prompt injection if the local files are untrusted.
- Ingestion points: Local files including
Containerfile,k8s/deployment.yaml,k8s/service.yaml,k8s/apirule.yaml, and.env.aicore. - Boundary markers: None.
- Capability inventory: Execution of
podman(build, tag, push) andkubectl(apply, create secret). - Sanitization: None. Because this ingestion is fundamental to the skill's primary purpose and uses standard tools, it is classified as safe.
Audit Metadata