gitops-cluster-debug
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it reads untrusted data from external sources and has tools to modify the environment.\n
- Ingestion points: Processes controller logs, resource status conditions, and Kubernetes metadata (referenced in SKILL.md via get_kubernetes_logs and get_kubernetes_resources).\n
- Boundary markers: Absent. The instructions do not specify the use of delimiters or guidelines to ignore instructions that might be embedded in the cluster data.\n
- Capability inventory: The skill possesses the ability to apply resources and change cluster contexts via apply_kubernetes_resource and set_kubeconfig_context.\n
- Sanitization: Absent. There is no explicit requirement or process for sanitizing log content or metadata before the agent analyzes it.
Audit Metadata