CC huawei-cloud-eip-cost-optimizer
Huawei Cloud EIP (Elastic IP) cost optimization skill using hcloud CLI (KooCLI). 1. List and query EIPs across regions with detailed status 2. Identify idle/unbound EIPs and generate cost optimization reports 3. Set up idle EIP monitoring with webhook/email alerts 4. Generate HTML/JSON cost analysis reports 5. Maintain operation audit logs for compliance **Read-only analysis only - NO bandwidth adjustment, tag management, or EIP release/deletion**. Triggers include: "EIP cost optimization", "idle EIP analysis", "EIP audit", "cost report", "EIP status query", "EIP list", "EIP monitoring", "EIP alert", "cost analysis", "idle monitoring", "operation audit", "EIP 成本优化", "闲置 EIP 分析", "EIP 审计", "成本报告", "EIP 状态查询", "EIP 查询", "EIP 列表", "EIP 监控", "EIP 告警", "成本分析", "闲置监控", "操作审计"
Huawei Cloud EIP (Elastic IP) cost optimization skill using hcloud CLI (KooCLI).
As a process C 63/100 · Has gaps — weak spots: when it triggers, failures and branches, running it twice
The same skill appears in 1 more place: ClawHub
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 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.
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.
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.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 11
-
high Dangerous commands
cmd-persistencescripts/monitor_idle_eips.sh:75Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null; echo "$cron_line") | crontab -
-
high Exfiltration
exfil-webhook-urlscripts/monitor_idle_eips.sh:153Webhook / callback URL commonly used for exfiltration (verify the destination)https://oapi.dingtalk.com/*|https://qyapi.weixin.qq.com/*|https://hooks.slack.com/*|https://*.api.slack.com/*)
Medium and low: 9
-
medium Dangerous commands
cmd-pipe-to-shellscripts/check_env.sh:75Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)# 安全安装: 下载到临时文件 → 校验 → 确认 → 执行 (避免 curl|bash 远程代码执行)
comment -
medium Dangerous commands
cmd-persistencescripts/monitor_idle_eips.sh:93Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)crontab -l 2>/dev/null | grep -vF "$CRON_MARKER" | crontab -
detector -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:54Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)curl -sSL https://hwcl…com/cli/latest/hcloud_install.sh | bash
security skill -
low Dangerous commands
cmd-pipe-to-shellreferences/acceptance-criteria.md:78Downloads and executes remote code from an unrecognised host (pipe to shell) (negated — the text forbids it)| 3 | No curl\|bash | `grep -r 'curl.*\|.*bash' scripts/` | No pipe-to-shell patterns |
negated -
low Dangerous commands
cmd-cron-mentionscripts/monitor_idle_eips.sh:69Mentions editing / listing crontabif crontab -l 2>/dev/null | grep -qF "$CRON_MARKER"; then
-
low Dangerous commands
cmd-cron-mentionscripts/monitor_idle_eips.sh:75Mentions editing / listing crontab(crontab -l 2>/dev/null; echo "$cron_line") | crontab -
-
low Dangerous commands
cmd-cron-mentionscripts/monitor_idle_eips.sh:88Mentions editing / listing crontabif ! crontab -l 2>/dev/null | grep -qF "$CRON_MARKER"; then
-
low Dangerous commands
cmd-cron-mentionscripts/monitor_idle_eips.sh:93Mentions editing / listing crontabcrontab -l 2>/dev/null | grep -vF "$CRON_MARKER" | crontab -
-
low Dangerous commands
cmd-autorun-instructionSKILL.md:403Instructs the agent to auto-run a script on every session (documentation of a security skill)7. **Environment Validation**: Always run `check_env.sh` first to verify hcloud CLI and dependencies
security skill
Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "id"
Process rating: all ten parameters 63/100
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4457 tokens
- 85Steps. 58 steps, 1 vague phrases
- 100Result and completion. Output format and completion criterion are stated
- 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 12 top-level sections: this looks like several domains in one skill
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 19 example trigger phrases
- +3Description length 780: enough signal without eating the budget
- +4Structure: 35 headings
- +3Step-by-step instructions: 58 items
- +3Output format is stated explicitly
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +3All 7 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.