BC wechat-miniapp-deploy
Deploy and manage WeChat Mini Programs (微信小程序) using the official miniprogram-ci CLI. Teach AI agents how to upload code, submit for review, manage versions, configure QR codes, and automate the full WeChat Mini Program deployment pipeline. Covers: first-time project setup and CI configuration, code upload with version management, review submission with privacy compliance, automated CI/CD pipeline for mini programs, multi-environment deployment (dev/staging/prod). Triggers on: 微信小程序部署, wechat mini program deploy, 小程序上传, miniapp upload, 小程序审核, mini program review, 小程序CI/CD, miniprogram-ci, 微信小程序发布, wechat miniapp publish, 小程序自动化部署, mini program automation, 小程序版本管理, miniapp version management, 小程序隐私合规, miniapp privacy compliance
Deploy and manage WeChat Mini Programs (微信小程序) using the official miniprogram-ci CLI.
As a process C 57/100 · Has gaps — weak spots: result and completion, failures and branches, 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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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
✓ No critical or high findings
Medium and low: 6
-
medium Exfiltration
exfil-secret-in-urlSKILL.md:159Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)ACCESS_TOKEN=$(curl -s "https://api.weixin.qq.com/cgi-bin/token?grant_type=…&appid=…&secret=…" | node -p "JSON.parse(require('fs').readFileSync('/dev/stdin','utf8')).accequoted -
medium Exfiltration
net-credential-useSKILL.md:159Credential used in a network call (verify the destination is the intended service)ACCESS_TOKEN=$(curl -s "https://api.weixin.qq.com/cgi-bin/token?grant_type=…&appid=…&secret=…" | node -p "JSON.parse(require('fs').readFileSync('/dev/stdin','utf8')).acce -
medium Exfiltration
net-credential-useSKILL.md:162Credential used in a network call (verify the destination is the intended service)curl -X POST "https://api.weixin.qq.com/wxa/submit_audit?access_token=…" \
-
low Exfiltration
exfil-secret-in-urlskill-card.md:29Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)- [WeChat access token API](https://api.weixin.qq.com/cgi-bin/token?grant_type=…&appid=…&secret=…) <br>
placeholder -
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 submit audit API](https://api.weixin.qq.com/wxa/submit_audit?access_token=…) <br>
placeholder -
low Exfiltration
exfil-secret-in-urlSKILL.md:162Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)curl -X POST "https://api.weixin.qq.com/wxa/submit_audit?access_token=…" \
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")
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 15 mutating operations with no state check
- 60Tools and files. Uses tools (git) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 15 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2256 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
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 736: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.