AB wechat-mp-draft-publisher
Publish WeChat Official Account draft articles through a packaged CLI executable that wraps WeChat API calls. Use when the user wants to publish or create a draft from local article content and images, especially when the required flow is getAuth -> uploadArticleImage -> uploadCoverImage -> addDraft.
As a process B 78/100 · Nearly there — weak spots: running it twice, progress reporting
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-usescripts/install_mp_weixin_skill.sh:118Credential used in a network call (verify the destination is the intended service)curl -fsSL -H "Authorization: Bearer ${GITHUB_TOKEN}" -H "Accept: application/octet-stream" -o "$tmp_file" "$asset_url" -
low Exfiltration
net-credential-usescripts/install_mp_weixin_skill.sh:87Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)release_json="$(curl -fsSL -H "Authorization: Bearer ${GITHUB_TOKEN}" -H "Accept: application/vnd.github+json" "$api_url")"quoted
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 78/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 20 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 718 tokens
- low The response is described with custom markup (3 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- -31 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 301: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 20 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.