gitops-cluster-debug
Pass
Audited by Gen Agent Trust Hub on May 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection by processing untrusted data directly from the Kubernetes cluster environment.\n
- Ingestion points: The skill retrieves pod logs, resource status conditions, and Kubernetes events using tools like get_kubernetes_logs and get_kubernetes_resources (as described in the debugging workflows in SKILL.md).\n
- Boundary markers: The instructions do not define specific delimiters or instructions to the model to ignore or isolate potentially malicious content embedded within the cluster data.\n
- Capability inventory: The skill has powerful capabilities, including the ability to apply resource manifests (apply_kubernetes_resource) and switch between different Kubernetes cluster contexts (set_kubeconfig_context).\n
- Sanitization: No evidence of sanitization or validation of the ingested cluster data is present before it is used for troubleshooting analysis.
Audit Metadata