CF aliyun-domain
Manage domain assets through Alibaba Cloud OpenAPI, supporting domain query, renewal, transfer, registration, and information modification. Requires user double confirmation for financial operations. Also provides Alibaba Cloud domestic domain promotion policy consultation, including registration activity prices, bulk registration discounts, transfer-in discounts, renewal discounts, and promotional codes. Added domain, website building, and filing industry consulting capabilities, based on RAG retrieval of local knowledge base (knowledge/aliyun-domain-help) to provide accurate answers. Added domain monitoring subscription functionality to monitor domain expiration time, WHOIS information changes, and SSL certificate status. Built-in creative domain naming capability, providing intelligent naming suggestions for projects/brands and checking availability.
As a process F 47/100 · Will not run — References files that are not bundled: SAFE_OPERATION_GUIDE.md
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 files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Obfuscation
obf-base64-blobknowledge/aliyun-domain-help/02-快速入门/从域名注册到网站搭建.md:123Long base64-looking blob
-
medium Dangerous commands
cmd-shell-rcSKILL.md:692Writes to a shell startup fileecho 'export ALIYUN_ACCESS_KEY_ID="your-access-key-id"' >> ~/.zshrc
-
medium Dangerous commands
cmd-shell-rcSKILL.md:693Writes to a shell startup fileecho 'export ALIYUN_ACCESS_KEY_SECRET="your-access-key-secret"' >> ~/.zshrc
Files scanned: 59. 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") - warning
body-longSKILL.md body ≈ 12022 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: SAFE_OPERATION_GUIDE.md - note
frontmatter-keyunknown frontmatter key "triggers"
Process rating: all ten parameters 47/100
- 0Tools and files. 1 referenced file(s) missing: SAFE_OPERATION_GUIDE.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Execution cost. Instruction body is 12022 tokens: crowds the task out of the window
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 6 branches
- 100Steps. 123 steps
- 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 17 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
- +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 865: 120–800 characters recommended
- -2139 emoji in the instructions: noise for the model
- -31 of 7 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 68 headings
- +3Step-by-step instructions: 123 items
- +3Output format is stated explicitly
- +4Has examples (36 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 50.