CC huawei-cloud-publish-work-to-gallery
Publish user's work to the Huawei Cloud University Operations Platform (华为云高校运营平台/作品陈列馆). Use this skill whenever the user wants to publish, submit, or upload a project/work to the gallery or a training camp (训练营) on the platform — including casual phrasings like "把作品发布上去", "投稿到陈列馆", "传作品到平台", "提交作品/项目", "报名发布作品", as well as formal ones like "publish to work gallery", "submit to training camp", "upload work to the platform". Do NOT use for general dev questions, git push to GitCode alone, or platform browsing without publishing intent.
Publish user's work to the Huawei Cloud University Operations Platform (华为云高校运营平台/作品陈列馆).
As a process C 53/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 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.
- 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 · 6
-
high Dangerous commands
cmd-pipe-to-shellreferences/devbridge-tunnel.md:8Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL https://res-hd.hc-cdn.cn/sharedata/hdspace/devbridge/install.sh | bash
-
high Dangerous commands
cmd-pipe-to-shellreferences/devbridge-tunnel.md:20Downloads and executes remote code from an unrecognised host (pipe to shell)> echo "y" | curl -fsSL https://res-hd.hc-cdn.cn/sharedata/hdspace/devbridge/install.sh | bash
Medium and low: 4
-
medium Exfiltration
net-redirectable-api-keyscripts/api.mjs:38Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
low Dangerous commands
cmd-execpolicy-bypassreferences/windows-setup.md:47Runs PowerShell with execution policy bypassed (quoted — discussed, not commanded)- 若 bash 不可用，改用 PowerShell 原生版：`powershell -ExecutionPolicy Bypass -File <skill>/scripts/pref…ps1`（与 preflight.sh 的 Windows 分支逻辑对齐，优先复用系统 Edge/Chrome，无需 bash）。
quoted -
low Dangerous commands
cmd-background-processreferences/work-preparation.md:175Starts a background / autostarted process> nohup python3 -m http.server 8099 > /tmp/httpserver.log 2>&1 &
-
low Dangerous commands
cmd-execpolicy-bypassscripts/preflight.ps1:2Runs PowerShell with execution policy bypassed (code comment)# 用法: powershell -ExecutionPolicy Bypass -File pref…ps1
comment
Files scanned: 39. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 8 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
- 100Steps. 38 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2975 tokens
- low The response is described with custom markup (35 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
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- -35 of 26 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 541: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 38 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (10 of 11)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.