BA huawei-cloud-cli-guidance
Provides guidance for Huawei Cloud KooCLI command-line tool operations. Covers KooCLI installation, IAM authentication configuration, access credential configuration, command construction, common error troubleshooting. Use this skill when users ask about any cloud-related services or wants to operate Huawei Cloud services from the terminal. Triggers: Huawei Cloud, huaweiyun, "华为云"，"华为cli", "命令行"， KooCLI, hcloud, huaweiyunCLI, Huawei Cloud command line, OBS, ECS, VPC, "云", yun， huaweiyun tool, huawei tool, "华为云工具", "云工具", "工具"
As a process A 89/100 · Runs to the end — no weak spots found
The same skill appears in 1 more place: ClawHub
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- 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 · 7
✓ No critical or high findings
Medium and low: 7
-
medium Dangerous commands
cmd-privilegereferences/installation-guide.md:49Privilege escalation / world-writable permissionssudo mv hcloud /usr/local/bin/
-
medium Dangerous commands
cmd-privilegereferences/installation-guide.md:54Privilege escalation / world-writable permissionssudo mv hcloud /usr/local/bin/
-
medium Dangerous commands
cmd-privilegereferences/installation-guide.md:73Privilege escalation / world-writable permissionssudo mv hcloud /usr/local/bin/
-
medium Dangerous commands
cmd-privilegereferences/installation-guide.md:78Privilege escalation / world-writable permissionssudo mv hcloud /usr/local/bin/
-
medium Dangerous commands
cmd-privilegereferences/installation-guide.md:157Privilege escalation / world-writable permissionssudo bash ./hcloud_install.sh
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash KooCLI
-
low Dangerous commands
cmd-privilegereferences/cli-troubleshooting.md:12Privilege escalation / world-writable permissions (documentation table row)| `hcloud: command not found` | KooCLI not installed or not in PATH | `sudo mv hcloud /usr/local/bin/` |
table
Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5423 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 89/100
- 50When it triggers. No condition that starts the skill
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5423 tokens
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 102 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 23 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (12 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)
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 531: enough signal without eating the budget
- +4Structure: 64 headings
- +3Step-by-step instructions: 102 items
- +3Output format is stated explicitly
- +4Has examples (16 code blocks)
- +4Reference files are cited in the instructions (8 of 8)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.