CA alibabacloud-cfw-nat-firewall-protect
Manage Alibaba Cloud Firewall (CFW) NAT Firewall (NAT boundary firewall): query firewalls and protection status, enable/disable the protection switch, assess which NAT gateways can be protected and produce a plan, run the creation pre-check, diagnose route-entry inconsistency (route-diff), prepare manual-mode diversion assets, create a firewall (auto or manual vswitch diversion), and change engine strict mode. Deleting/releasing a firewall is NOT supported: protection can be switched off, but the resource must be released by the user in the console. Use when users mention NAT firewall, NAT boundary firewall, NAT gateway protection, protecting private-network outbound traffic, opening/closing the NAT firewall switch, assessing how to enable protection, or diagnosing creation failures from inconsistent custom route entries. 管理阿里云云防火墙（CFW）NAT边界防火墙：查询防火墙与防护状态、开启/关闭防护开关、开墙评估与开墙方案、 创建预检查、路由条目不一致诊断、手动引流准备、创建NAT防火墙、修改引擎模式。不支持删除/释放防火墙， 需用户在控制台自行操作。适用于NAT防火墙、NAT网关防护、私网出方向防护、开关NAT墙、开墙评估等场景。
Manage Alibaba Cloud Firewall (CFW) NAT Firewall (NAT boundary firewall): query firewalls and protection status, enable/disable the protection switch, assess…
As a process A 80/100 · Runs to the end — weak spots: result and completion, execution cost
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.
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
- 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.
- 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 · 5
-
high Dangerous commands
cmd-pipe-to-shellscripts/validate-cli.sh:71Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL --connect-timeout 10 --max-time 120 https://aliyuncli.alicdn.com/setup.sh | bash
Medium and low: 4
-
medium Dangerous commands
cmd-pipe-to-shellscripts/validate-cli.sh:131Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)log_warn "CLI version ${CLI_VERSION} is below minimum ${MIN_CLI_VERSION}. Run: curl -fsSL --connect-timeout 10 --max-time 120 https://aliyuncli.alicdn.com/setup.sh | bash"code literal -
medium Dangerous commands
cmd-pipe-to-shellscripts/validate-cli.sh:135Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)log_warn "Alibaba Cloud CLI not installed. Install with: curl -fsSL --connect-timeout 10 --max-time 120 https://aliyuncli.alicdn.com/setup.sh | bash"
code literal -
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:73Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)curl -fsSL --connect-timeout 10 --max-time 120 https://aliyuncli.alicdn.com/setup.sh | bash
security skill
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 11471 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 80/100
- 40Result and completion. Does not say what the result is
- 40Execution cost. Instruction body is 11471 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 85Steps. 59 steps, 2 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 8 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 16 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (6 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)
- +3Description length 994: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 21 headings
- +3Step-by-step instructions: 59 items
- +4Has examples (20 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +3All 4 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.