CB volcengine-cli
Create and manage Volcengine cloud resources using the Volcengine CLI (`ve` command). Supports all Volcengine services including ECS, VPC, CLB, RDS, Redis, and more. Trigger this skill whenever the user asks to create, query, modify, or delete cloud resources on Volcengine, mentions the `ve` command, says "volcengine CLI", or describes infrastructure tasks such as "create an ECS instance", "set up a VPC", "list security groups", "allocate an EIP". Also trigger on Chinese prompts mentioning "火山引擎" or "火山" (e.g., "火山引擎上有哪些 ECS"、"查一下我火山的云服务器"、 "火山引擎创建一个 VPC"、"火山的 Redis 实例列一下"). Also trigger when the user encounters errors from `ve` commands and needs troubleshooting help.
As a process B 75/100 · Nearly there — weak spots: inputs and preconditions, running it twice
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 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
- 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 · 16
✓ No critical or high findings
Medium and low: 16
-
medium Dangerous commands
cmd-pipe-to-shellscripts/install_ve.sh:13Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)# curl -fsSL https://cloudcache.volccdn.com/ve/install.sh | sh
comment -
medium Dangerous commands
cmd-pipe-to-shellscripts/install_ve.sh:14Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)# wget -qO- https://cloudcache.volccdn.com/ve/install.sh | sh
comment -
medium Dangerous commands
cmd-quarantine-filescripts/install_ve.sh:315Removes the macOS quarantine flag from one file (usual for a downloaded CLI; make sure the file is the intended binary)xattr -d com.apple.quarantine "$staged" 2>/dev/null || true
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:86Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)curl -fsSL https://cloudcache.volccdn.com/ve/install.sh | sh
security skill -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:88Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)wget -qO- https://cloudcache.volccdn.com/ve/install.sh | sh
security skill -
low Dangerous commands
cmd-background-processreferences/common-errors.md:57Starts a background / autostarted process (documentation table row; documentation of a security skill)| A managed runner killed background descendants when the launching call returned | `status` said `ALIVE` earlier, `DEAD` now, with no user approval in between | Retry `start` once. The helper launche
tablesecurity skill -
low Dangerous commands
cmd-background-processreferences/console-login.md:99Starts a background / autostarted process (negated — the text forbids it)- ❌ Do NOT substitute `nohup ... &` for `start`. `nohup` only ignores SIGHUP and leaves ve in the caller's process group, so group cleanup still kills it. The script already uses `setsid`, which is wh
negated -
low Dangerous commands
cmd-background-processreferences/ecs.md:84Starts a background / autostarted process (documentation of a security skill)systemctl enable --now docker
security skill -
low Dangerous commands
cmd-background-processscripts/ve_login_remote.sh:30Starts a background / autostarted process (string literal in code, not executed; code comment)# Detaching uses `setsid` where available (Linux). macOS ships no `setsid`,
code literalcomment -
low Dangerous commands
cmd-background-processscripts/ve_login_remote.sh:31Starts a background / autostarted process (string literal in code, not executed; code comment)# so the script falls back to perl's POSIX::setsid, then to a plain
code literalcomment -
low Dangerous commands
cmd-background-processscripts/ve_login_remote.sh:277Starts a background / autostarted processif command -v setsid >/dev/null 2>&1; then
-
low Dangerous commands
cmd-background-processscripts/ve_login_remote.sh:278Starts a background / autostarted processdetach=(setsid)
-
low Dangerous commands
cmd-background-processscripts/ve_login_remote.sh:280Starts a background / autostarted process (negated — the text forbids it)# macOS has no setsid(1) but always ships perl.
negated
A further 3 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 28. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5936 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 75/100
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 12 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 5936 tokens
- 100Steps. 53 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 6 branches, has a failure section
- 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 The response is described with custom markup (16 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
- +4Description does not say when NOT to use the skill (false activations)
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +3Description length 677: enough signal without eating the budget
- +4Structure: 28 headings
- +3Step-by-step instructions: 53 items
- +3Output format is stated explicitly
- +4Has examples (17 code blocks)
- +4Reference files are cited in the instructions (21 of 21)
- +3All 5 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.