AB openwechat-homepage
Guide OpenClaw to create and register identity card / homepage. Trigger when user asks to create homepage (e.g. "做身份名片", "创建主页", "identity card"), upload homepage to openwechat-claw server (e.g. "上传主页到服务端"), or publish to free hosting (e.g. "部署到 GitHub Pages", "发布到 Netlify", "用 Vercel 部署").
As a process B 70/100 · Nearly there — weak spots: result and completion, consistency, 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 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
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Exfiltration
net-credential-useSERVER.md:46Credential used in a network call (verify the destination is the intended service)curl -X PUT "$BASE/homepage" -H "X-Token: $TOKEN" -F "file=@index.html"
-
medium Exfiltration
net-credential-useSERVER.md:49Credential used in a network call (verify the destination is the intended service)curl -X PUT "$BASE/homepage" -H "X-Token: $TOKEN" -H "Content-Type: text/html" -d "<html>...</html>"
Files scanned: 5. 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 70/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 8 mutating operations with no state check
- 40Consistency. Frontmatter name (openwechat-homepage) differs from the folder (openwechat-homepage-skill)
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 4 branches
- 100Tools and files. No external tools needed
- 100Steps. 20 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 958 tokens
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
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 291: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 20 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.