ascend-envcheck

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requests SSH passwords or private key paths and shows example commands (sshpass -p '' and ssh -i <key_path>) that require embedding those secrets verbatim into generated commands, which creates a high exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). 该 skill 的运行时工作流通过 SSH 上传并执行 scripts/envCheck.sh，而脚本会直接用 kubectl/jq 读取集群内各类 Kubernetes 资源（如 kubectl get node ... -o json、kubectl get cm ... -o jsonpath=...、kubectl logs ...），这些资源的字段值可能包含由外部用户/恶意操作者写入的自由文本，从而在运行时被 LLM 读取与格式化输出（间接提示注入风险）。