What is huawei-cloud-devkit-webui-create?

An installation procedure for running Huawei Kunpeng DevKit in WebUI mode on a Huawei Cloud virtual machine using the Kunpeng ARM-based processor architecture.

Use it to create the cloud server, configure its network access, securely handle its password, connect over SSH, and install Kunpeng DevKit.

It separates cloud setup, encryption, and SSH installation steps while keeping the generated machine password out of command arguments and environment variables.

huawei-cloud-devkit-webui-create — Skill for Claude Code and Codex by

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-devkit-webui-create

Clone the repo

git clone --depth 1 https://github.com/huaweicloud/huaweicloud-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-devkit-webui-create/github.svg)](https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-devkit-webui-create)

Your own site

<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-devkit-webui-create"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-devkit-webui-create/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-devkit-webui-create"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-devkit-webui-create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 201 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,960 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Rogue Agent · line 216
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00201	$0.06960
Opus 5	$0.00101	$0.03480
Sonnet 5	$0.00040	$0.01392
Haiku 4.5	$0.00020	$0.00696

Measured 11d ago against content hash 4484b643302e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

huawei-cloud-devkit-webui-create scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/create_ecs_and_setup_devkit.py, scripts/install_devkit_webui.sh, scripts/poll_devkit_status.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

> - **Last log lines**: PREPARING → from `/tmp/devkit_install_wrapper.log` (yum/wget output); RUNNING/DONE → from `/tmp/devkit_install.log`

skills/computing/kunpeng/huawei-cloud-devkit-webui-create/SKILL.md · 404 lines

How it starts

The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kunpeng DevKit WebUI Installation Skill

Overview

Create a Kunpeng (aarch64) ECS instance via Python SDK (ECS + KMS), use hcloud CLI for cloud operations (EIP, VPC), use Python paramiko SSH to connect and install Kunpeng DevKit in WebUI mode. Password never leaves Python process memory.

Tool separation principle:

Python SDK — ECS creation + KMS encrypt/decrypt/delete (password never leaves Python process memory, never appears in ps -ef)
hcloud CLI — All other cloud operations (EIP create/bind, VPC query, security group)
Python paramiko — SSH connection + DevKit installation (password from KMS decrypt, stays in Python memory only)

Security architecture:

ECS password is randomly generated by Python code (never typed by user, never passed via hcloud CLI, never exported to shell)
Password is encrypted and stored in Huawei Cloud KMS via Python SDK (never appears in ps -ef, env vars, or conversation)
Password is decrypted from KMS and passed to paramiko SSHClient.connect(password=...) (in Python process memory, not CLI args → no ps -ef leakage)
Only kms_key_id and kms_cipher_text_file are exported (password itself is never exported; cipher text is written to a local file, never passed via command line)
KMS key is scheduled for deletion after DevKit installation
No COC dependency, no UniAgent dependency, no third-party skill dependency

⛔ Prohibited Operations (Security Constraints)

This skill strictly forbids the following operations, regardless of user requests:

Prohibited Operation	Reason
❌ Use `--server.adminPass` in `hcloud ECS CreateServers`	Password appears in `ps -ef` output
❌ Use `hcloud AOM BatchImportAgent --agent_import_param_list.1.password=...`	Password appears in `ps -ef` output
❌ Accept ECS password in chat conversation	Password must never appear in conversation
❌ Use `expect` + `$env(DEVKIT_ECS_PASSWORD)` for SSH	Environment variable can be read by other processes
❌ Use `sshpass -p <password>` for SSH	Password appears in `ps -ef` output
❌ Use `ssh -o PasswordAuthentication` with password on CLI	Password appears in `ps -ef` output
❌ Hardcode password in scripts or command-line arguments	Password exposure risk
❌ Use `question` tool to ask user for password	Password must never appear in conversation
❌ Print or log the ECS password in any output	Password must only exist in Python process memory and KMS
❌ Export password to shell variables or stdout	Password must stay in Python process; only KMS key_id and cipher_text_file path are exported
❌ Pass KMS cipher text via command line arguments	Cipher text appears in `ps -ef`; must use `--kms-cipher-text-file` to read from local file
❌ Auto-select ECS flavor or image without user confirmation	Must let user choose from available options
❌ Display aarch64 images other than CentOS 7.6 and Ubuntu 18.04	Only these two images are compatibility-verified
❌ Select x86 flavors (c6/c7 etc.)	DevKit requires aarch64 (Kunpeng) architecture
❌ Skip security group port confirmation	Ports 22 and 8086 must be opened before SSH
❌ Auto-modify security group rules without user consent	Must ask user to choose manual or automatic mode
❌ Write new install/verify scripts instead of using existing ones	Must use scripts in `scripts/` directory
❌ Disable or delete KMS key when installation verification fails	KMS key must be preserved for retry; only destroy after verified success (via Task 4 cleanup-kms)
❌ Run cleanup-kms before Task 3 verification passes	KMS key must be preserved until agent confirms DevKit installation success
❌ Run expect script without verifying `expect` binary is installed	Shebang `#!/usr/bin/expect -f` fails with misleading "No such file or directory" if expect is missing

Read the full file on GitHub · 404 lines

Files

What ships with it

17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

11d ago First seen · 404 lines · 201 tokens per session scan A 4484b643302e

Subscribe to this mod's changes

huawei-cloud-devkit-webui-create is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (48 stars, last pushed yesterday), licensed MIT. It adds 201 tokens to every session and 6,960 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Cloud DevOps and cloud devkit devkit webui kunpeng

gke-compute-classes

Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…

google/skills · 83 tokens

gke-reliability

Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).

google/skills · 73 tokens

gke-workload-security

Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…

google/skills · 181 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens

cloud-architect

Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…

Jeffallan/claude-skills · 71 tokens

huawei-cloud-devkit-webui-create