BF huawei-cloud-devkit-webui-create
Install Kunpeng DevKit in WebUI mode on Huawei Cloud. Create a Kunpeng (aarch64) ECS via Python SDK with random password, encrypt password via Python KMS SDK, use hcloud CLI for EIP/VPC operations, use Python paramiko SSH (password in process memory only) to install DevKit-All-x.x.x-Linux-Kunpeng.tar.gz, including framework and all plugins (porting/affinity/devtools/debugger/sys_perf/java_perf/sys_diagnosis). Use this skill when the user wants to: (1) install DevKit on a new Kunpeng ECS, (2) install DevKit on an existing Kunpeng ECS. Trigger: user mentions "DevKit", "Kunpeng DevKit", "install DevKit", "DevKit WebUI", "Kunpeng DevKit", "DevKit-All", "鲲鹏DevKit", "安装DevKit", "鲲鹏开发套件"
Install Kunpeng DevKit in WebUI mode on Huawei Cloud.
As a process F 63/100 · Will not run — References files that are not bundled: scripts/auto_install_devkit.expect
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
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
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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
✓ No critical or high findings
Medium and low: 8
-
medium Dangerous commands
cmd-shell-rcreferences/cli-installation-guide.md:33Writes to a shell startup fileecho 'export PATH="$PATH:$HOME/.local/bin"' >> ~/.bashrc
-
medium Dangerous commands
cmd-privilegereferences/cli-installation-guide.md:47Privilege escalation / world-writable permissionssudo mv hcloud /usr/local/bin/
-
medium Dangerous commands
cmd-privilegereferences/cli-installation-guide.md:56Privilege escalation / world-writable permissionssudo mv hcloud /usr/local/bin/
-
medium Dangerous commands
cmd-privilegereferences/cli-installation-guide.md:65Privilege escalation / world-writable permissionssudo mv hcloud /usr/local/bin/
-
low Dangerous commands
cmd-background-processreferences/devkit-installation-guide.md:355Starts a background / autostarted processnohup /tmp/auto_install_devkit.expect > /tmp/devkit_install.log 2>&1 &
-
low Dangerous commands
cmd-background-processreferences/devkit-installation-workflow.md:161Starts a background / autostarted processnohup /tmp/auto_install_devkit.expect > /tmp/devkit_install.log 2>&1 &
-
low Dangerous commands
cmd-background-processscripts/install_devkit_webui.sh:225Starts a background / autostarted processnohup ${EXPECT_SCRIPT} ${EXPECT_ARGS} > "${INSTALL_LOG}" 2>&1 & -
low Dangerous commands
cmd-background-processscripts/install_devkit_webui.sh:227Starts a background / autostarted processnohup ${EXPECT_SCRIPT} > "${INSTALL_LOG}" 2>&1 &
Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6619 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: scripts/auto_install_devkit.expect
Process rating: all ten parameters 63/100
- 0Tools and files. 1 referenced file(s) missing: scripts/auto_install_devkit.expect
- 30Running it twice. 45 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 6619 tokens
- 85Steps. 32 steps, 1 vague phrases
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 2 branches, has a failure section
- 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 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 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)
- +3Output format is not stated: the model decides each time
- -235 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +3Description length 689: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 32 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (12 of 12)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.