DB alibabacloud-devops
Automate Alibaba Cloud Yunxiao DevOps tasks — create and run pipelines, manage code repositories and merge requests, track work items and sprints, create test cases, manage artifacts, and drive application release workflows across 8 Yunxiao products. Triggers: "Yunxiao", "DevOps", "pipeline", "code repository", "merge request", "work item", "sprint", "test case", "application delivery", "artifact repository", "Codeup", "Flow", "Projex", "AppStack", "Packages", "Testhub"
Automate Alibaba Cloud Yunxiao DevOps tasks — create and run pipelines, manage code repositories and merge requests, track work items and sprints, create test…
As a process B 74/100 · Nearly there — weak spots: result and completion
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 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.
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.
- 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 Exfiltration
net-credential-usereferences/acceptance-criteria.md:127Credential used in a network call (verify the destination is the intended service)curl -H "Authorization: Bearer $YUNXIAO_ACCESS_TOKEN" ... [X] (may leak to logs)
-
medium Dangerous commands
cmd-privilegereferences/aliyun-cli-install.md:48Privilege escalation / world-writable permissionssudo mv ./aliyun /usr/local/bin/
-
medium Dangerous commands
cmd-privilegereferences/aliyun-cli-install.md:82Privilege escalation / world-writable permissionssudo mv ./aliyun /usr/local/bin/
-
medium Dangerous commands
cmd-execpolicy-bypassreferences/aliyun-cli-install.md:94Runs PowerShell with execution policy bypassedpowershell.exe -ExecutionPolicy Bypass -File C:\Example\Inst…ps1
-
medium Dangerous commands
cmd-execpolicy-bypassreferences/aliyun-cli-install.md:100Runs PowerShell with execution policy bypassedpowershell.exe -ExecutionPolicy Bypass -File C:\Example\Inst…ps1 -Version 3.3.15 -InstallDir "C:\ExampleDir\AliyunCLI"
-
medium Dangerous commands
cmd-execpolicy-bypassreferences/aliyun-cli-install.md:241Runs PowerShell with execution policy bypassedpowershell.exe -ExecutionPolicy Bypass -File C:\Example\Inst…ps1
-
medium Dangerous commands
cmd-privilegereferences/aliyun-cli-install.md:262Privilege escalation / world-writable permissionssudo rm -v $(which aliyun)
Files scanned: 17. 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 ≈ 6184 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 74/100
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70Execution cost. Instruction body is 6184 tokens
- 85Steps. 39 steps, 2 vague phrases
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 2 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 10 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)
- +3Output format is not stated: the model decides each time
- -31 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 15 example trigger phrases
- +3Description length 474: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 39 items
- +4Has examples (20 code blocks)
- +4Reference files are cited in the instructions (12 of 12)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.