BF wechat-mp-draft
代写微信公众号文章并保存到公众号草稿箱。使用场景：用户需要撰写公众号文章并直接发布到微信公众号后台草稿箱；或排查公众号草稿箱里的「标题在文章顶部重复显示两次」「标题行既出现在 title 字段又出现在 body」等 markdown-renderer 标题重复问题。触发词："写公众号文章"、"保存到公众号草稿"、"微信文章"、"公众号发文"、"标题重复"、"草稿标题显示两次"。
As a process F 35/100 · Will not run — References files that are not bundled: ../wechat-markdown-html-render/
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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Exfiltration
exfil-secret-in-urlSKILL.md:151Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)curl -s -X POST "https://api.weixin.qq.com/cgi-bin/draft/batchget?access_token=…" \
quoted -
medium Exfiltration
net-credential-useSKILL.md:151Credential used in a network call (verify the destination is the intended service)curl -s -X POST "https://api.weixin.qq.com/cgi-bin/draft/batchget?access_token=…" \
-
low Exfiltration
exfil-secret-in-urlskill-card.md:30Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)- [WeChat draft batchget endpoint](https://api.weixin.qq.com/cgi-bin/draft/batchget?access_token=…) <br>
placeholder
Files scanned: 2. 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
missing-refreference to a missing file: ../wechat-markdown-html-render/
Process rating: all ten parameters 35/100
- 0Tools and files. 1 referenced file(s) missing: ../wechat-markdown-html-render/
- 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
- 20When it triggers. No condition that starts the skill
- 100Steps. 36 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2152 tokens
- 100Running it twice. No mutating operations
- low The response is described with custom markup (6 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 190: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 36 items
- +4Has examples (15 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.