SKILLEMALL.ai
GitHub ↗ RU Sign in

BF wechat-mp-publisher

WeChat Official Account (微信公众号) draft push and auto-publish toolkit. This skill should be used when the user wants to push article drafts to a WeChat Official Account draft box via API, publish drafts automatically on a schedule, or set up a daily publishing automation. Covers credential setup, IP whitelisting, draft creation, and freepublish/submit publishing. Triggers: push draft, publish to WeChat, auto-publish, 微信发布, 推送草稿, 自动发布, 公众号发布.

ClawHub Agent Skills author: yyi162751-collab v1.0.0 MIT-0 7 files · 1 script body ≈ 1 265 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

WeChat Official Account (微信公众号) draft push and auto-publish toolkit.

As a process F 44/100 · Will not run — References files that are not bundled: assets/.env.example

GeneratorWriting and documentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
87/100
safety, quality, tests
Safety 60%
89
Quality 40%
84
Run on models
none yet
Process rating
F
44/100
Will not run
References files that are not bundled: assets/.env.example
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

The same skill appears in 1 more place: ClawHub

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

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".

For the author

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

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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 · 7

✓ No critical or high findings

Medium and low: 7
  • medium Exfiltration net-credential-use scripts/wechat_api.sh:38
    Credential used in a network call (verify the destination is the intended service)
    response=$(curl -s "https://api.weixin.qq.com/cgi-bin/token?grant_type=…&appid=…&secret=…")
  • low Exfiltration exfil-secret-in-url scripts/wechat_api.sh:38
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    response=$(curl -s "https://api.weixin.qq.com/cgi-bin/token?grant_type=…&appid=…&secret=…")
    placeholder
  • low Exfiltration exfil-secret-in-url scripts/wechat_api.sh:68
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    "https://api.weixin.qq.com/cgi-bin/material/add_material?access_token=…&type=image" \
    placeholder
  • low Exfiltration exfil-secret-in-url scripts/wechat_api.sh:89
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    "https://api.weixin.qq.com/cgi-bin/draft/add?access_token=…" \
    placeholder
  • low Exfiltration exfil-secret-in-url scripts/wechat_api.sh:103
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    "https://api.weixin.qq.com/cgi-bin/freepublish/submit?access_token=…" \
    placeholder
  • low Exfiltration exfil-secret-in-url scripts/wechat_api.sh:118
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    "https://api.weixin.qq.com/cgi-bin/draft/batchget?access_token=…" \
    placeholder
  • low Exfiltration read-dotenv SKILL.md:25
    Reads a .env file
    cp assets/.env.example ~/.wechat-mp.env

Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: assets/.env.example
  • note frontmatter-key unknown frontmatter key "agent_created"

Process rating: all ten parameters 44/100

Will not run. References files that are not bundled: assets/.env.example
  • 0Tools and files. 1 referenced file(s) missing: assets/.env.example
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 34 mutating operations with no state check
  • 40Consistency. Frontmatter name (wechat-mp-publisher) differs from the folder (wechat-mp-publish-toolkit)
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 32 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Execution cost. Instruction body is 1265 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

  • +5Description has no quoted example phrases that should trigger the skill
  • +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
  • +3Description length 443: enough signal without eating the budget
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 32 items
  • +4Has examples (6 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)
  • +3All 3 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

External checks

ClawHub: suspicious
This is a disclosed WeChat publishing toolkit, but it can use account secrets to automatically publish or delete official-account content without built-in confirmation controls.
LLM: suspicious (high) · 18 Jul 2026