CB huawei-cloud-cce-workload-manager
Huawei Cloud CCE/UCS workload lifecycle management skill using hcloud CLI for kubeconfig acquisition and kubectl for Kubernetes resource operations. Use this skill when the user wants to: (1) obtain kubeconfig for CCE clusters, (2) obtain federation kubeconfig for UCS fleet (multi-cluster operations), (3) manage Deployment/StatefulSet/DaemonSet/Job/CronJob lifecycle, (4) configure HPA autoscaling, (5) manage Service/Ingress/ConfigMap/Secret/PVC, (6) observe Pod status/logs/events, (7) manage namespaces, (8) install and configure kubectl. Trigger: user mentions "CCE workload", "k8s workload", "UCS fleet workload", "Deployment", "StatefulSet", "DaemonSet", "Job", "CronJob", "HPA", "kubectl", "kubeconfig", "federation kubeconfig", "Pod logs", "CCE 负载", "UCS 联邦负载", "工作负载", "部署", "有状态副本集", "守护进程集", "任务", "定时任务", "弹性伸缩", "服务", "路由", "配置项", "密钥", "存储卷", "Pod 日志", "命名空间"
Huawei Cloud CCE/UCS workload lifecycle management skill using hcloud CLI for kubeconfig acquisition and kubectl for Kubernetes resource operations.
As a process B 74/100 · Nearly there — weak spots: running it twice
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 8
-
high Exfiltration
exfil-read-secret-filesreferences/task-kubectl-setup.md:175Reads credential / secret filescp cce-kubeconfig.yaml ~/.kube/config
Medium and low: 7
-
medium Dangerous commands
cmd-privilegereferences/task-kubectl-setup.md:38Privilege escalation / world-writable permissionsecho 'deb [signed-by=/usr/share/keyrings/kubernetes-apt-keyring.gpg] https://pkgs.k8s.io/core:/stable:/v1.28/deb/ /' | sudo tee /etc/apt/sources.list.d/kubernetes.list
-
medium Dangerous commands
cmd-privilegereferences/task-kubectl-setup.md:49Privilege escalation / world-writable permissionscat <<EOF | sudo tee /etc/yum.repos.d/kubernetes.repo
-
medium Dangerous commands
cmd-privilegereferences/task-kubectl-setup.md:75Privilege escalation / world-writable permissionssudo mv ./kubectl /usr/local/bin/kubectl
-
medium Dangerous commands
cmd-privilegereferences/task-kubectl-setup.md:76Privilege escalation / world-writable permissionssudo chown root: /usr/local/bin/kubectl
-
medium Dangerous commands
cmd-shell-rcreferences/task-kubectl-setup.md:224Writes to a shell startup fileecho 'source <(kubectl completion bash)' >>~/.bashrc
-
medium Dangerous commands
cmd-shell-rcreferences/task-kubectl-setup.md:234Writes to a shell startup fileecho 'source <(kubectl completion zsh)' >>~/.zshrc
-
medium Dangerous commands
cmd-shell-rcreferences/task-kubectl-setup.md:237Writes to a shell startup fileecho 'autoload -Uz compinit && compinit' >>~/.zshrc
Files scanned: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5730 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "id"
Process rating: all ten parameters 74/100
- 30Running it twice. 43 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5730 tokens
- 100Steps. 72 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (11 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 875: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 15 example trigger phrases
- +4Structure: 23 headings
- +3Step-by-step instructions: 72 items
- +3Output format is stated explicitly
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (4 of 14)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.