k8s-launch-kit-validate
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
l8k validatecommand to perform validation of Kubernetes deployments. - [DATA_EXFILTRATION]: The skill accesses the sensitive file path
~/.kube/configto retrieve credentials necessary for communicating with the Kubernetes cluster. - [DATA_EXFILTRATION]: The skill reads Helm release Secrets from the cluster environment to verify the version of the installed Network Operator.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting external YAML configuration and manifest files to determine the cluster's state.
- Ingestion points: Reads
cluster-config.yamland YAML manifest files located in the--deployment-filesdirectory. - Boundary markers: None identified in the skill instructions.
- Capability inventory: The skill has the capability to execute the
l8kcommand-line tool. - Sanitization: There is no evidence of sanitization for the ingested manifest data before it is processed by the validation tool.
Audit Metadata