kubesense-skills

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill example shows a CLI command that includes an API key header passed inline (--header "x-api-key: "), which would require the agent to insert secret values verbatim into generated commands or outputs.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). kubesense-infra’s runtime reads cluster/namespace/workload/pod names provided by the user by calling tools like list-clusters first and then passing unvalidated free-text clusters into subsequent inventory tools, which can include outsider-authored strings from the user request.