SKILLEMALL.ai
GitHub ↗ RU Sign in

DC huawei-cloud-apig-instance-management

Manage Huawei Cloud APIG (API Gateway, dedicated instances) via hcloud CLI: instance lifecycle (create/list/delete), API groups, API create/update/delete, publish/offline, request throttling policies, signature keys, access control (ACL) policies, and public ingress EIP binding, plus read-only diagnosis of public access (eip_address vs sl_domain), the instance -> group -> API -> publish chain, and policy effectiveness. Delete operations require explicit user confirmation; instance creation is a 5-15 minute async operation that must be polled until status == Running. Triggers include: APIG, API gateway, API 分组, API 管理, 流控策略, throttling, 签名密钥, signature key, 访问控制, ACL 策略, access control, publish API, 发布 API, 下线 API, 实例管理, 公网访问, ingress EIP, 策略生效诊断, API 网关排障.

ClawHub Agent Skills author: huaweicloudskill v1.0.3 MIT-0 10 files · 3 scripts body ≈ 9 314 tokens Open the sourceclawhub.ai↗ analyzed 5 d ago

Manage Huawei Cloud APIG (API Gateway, dedicated instances) via hcloud CLI: instance lifecycle (create/list/delete), API groups, API create/update/delete…

As a process C 59/100 · Has gaps — weak spots: result and completion, when it triggers, execution cost

IntegrationPeople and hiringtype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
D
73/100
safety, quality, tests
Safety 60%
75
Quality 40%
69
Run on models
none yet
Process rating
C
59/100
Has gaps
Progress reporting w 2
0
When it triggers w 12
20
Result and completion w 14
40
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

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.

For the author

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

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • 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 · 13

✓ No critical or high findings

Medium and low: 13
  • medium Dangerous commands cmd-shell-rc scripts/ensure_cli.sh:22
    Writes to a shell startup file
    echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc
  • medium Dangerous commands cmd-shell-rc scripts/ensure_cli.sh:25
    Writes to a shell startup file
    echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.profile
  • medium Dangerous commands cmd-shell-rc scripts/ensure_cli.sh:53
    Writes to a shell startup file
    echo "PATH 已导出并持久化(~/.bashrc ~/.profile), 可直接执行: skill-quality-cli ..."
  • low Secrets in code secret-high-entropy-token references/acceptance-criteria.md:37
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    `Crea…yV2`, `List…yV2`,
    quoted
  • low Secrets in code secret-high-entropy-token references/acceptance-criteria.md:40
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    `List…yV2`, `List…yV2`,
    quoted
  • low Secrets in code secret-high-entropy-token references/acceptance-criteria.md:41
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    `List…yV2`
    detector
  • low Secrets in code secret-high-entropy-token references/dataflow-diagram.md:63
    High-entropy token-like string (may be an id, hash or a credential)
    Q -->|verify exists| A[huawei_analyze_apig_policy_effect<br/>List…yV2]
  • low Secrets in code secret-high-entropy-token references/verification-method.md:42
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; documentation table row)
    | `huawei_create_apig_throttling_policy` | `List…yV2 --instance_id` contains the new policy |
    detectortable
  • low Secrets in code secret-high-entropy-token SKILL.md:75
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; documentation table row)
    | 7 | API / throttling policy names must NOT have hyphens | `[a-zA-Z0-9_]+` only. Hyphens cause regex validation failure (verified for `Crea…yV2` too, APIG.2011). |
    detectortable
  • low Secrets in code secret-high-entropy-token SKILL.md:198
    High-entropy token-like string (may be an id, hash or a credential)
    hcloud APIG List…yV2 --cli-region={region} --instance_id={instance_id} --limit=20
  • low Secrets in code secret-high-entropy-token SKILL.md:199
    High-entropy token-like string (may be an id, hash or a credential)
    skill-quality-cli run --skill-name huawei-cloud-apig-instance-management -- hcloud APIG List…yV2 --cli-region={region} --instance_id={instance_id} --limit=20
  • low Secrets in code secret-high-entropy-token SKILL.md:294
    High-entropy token-like string (may be an id, hash or a credential)
    hcloud APIG List…yV2 --cli-region={region} --instance_id={instance_id} --sign_id={sign_id}
  • low Secrets in code secret-high-entropy-token SKILL.md:298
    High-entropy token-like string (may be an id, hash or a credential)
    hcloud APIG List…yV2 --cli-region={region} --instance_id={instance_id} --throttle_id={throttle_id}

Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 9314 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 59/100

  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 40Result and completion. Does not say what the result is
  • 40Execution cost. Instruction body is 9314 tokens: crowds the task out of the window
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 16 steps, 1 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 10 top-level sections: this looks like several domains in one skill
  • high The skill tells the model to perform an irreversible action with no human approval
  • low The response is described with custom markup (7 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

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 766: enough signal without eating the budget
  • +4Structure: 34 headings
  • +3Step-by-step instructions: 16 items
  • +4Has examples (27 code blocks)
  • +4Reference files are cited in the instructions (5 of 5)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.

External checks

ClawHub: suspicious
The APIG management instructions are mostly coherent, but the skill mandates a persistent telemetry wrapper that can send unredacted cloud command output and local agent session metadata to a remote service.
LLM: suspicious (high) · 28 Sept 2026