chatqna-helm-deploy
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches Helm charts from Intel's official repository on Docker Hub (registry-1.docker.io/intel/). These downloads are from a well-known service and a trusted organization.
- [COMMAND_EXECUTION]: The skill uses standard CLI tools such as
kubectl,helm,jq, andcurlto interact with the Kubernetes cluster, manage deployments, and verify service health. These operations are consistent with the skill's primary purpose of application deployment. - [INDIRECT_PROMPT_INJECTION]: The skill ingests user inputs and environment variables to generate
values-override.yamlfiles. While this represents an ingestion point for untrusted data, the skill mitigates risk by instructing the user to use environment variable placeholders rather than hardcoding secrets, and the processing is local to the deployment environment. - Ingestion points: Environment variables (e.g.,
HUGGINGFACEHUB_API_TOKEN, proxy settings) and user-supplied CLI arguments inSKILL.md. - Boundary markers: None explicitly present in the generated YAML templates, but instructions emphasize safe secret handling.
- Capability inventory: Subprocess calls to
helm upgrade,kubectl apply, andcurlfor deployment and health checks. - Sanitization: Relies on standard Helm YAML parsing and shell environment variable interpolation.
Audit Metadata