Security audit
Security checks for vulnerabilities and agentic risk
This is a disclosed WeChat writing and publishing reference skill with no bundled executable code or hidden persistence, but users should treat final publishing as a live account action.
Install only if you intend to use it for WeChat public-account workflows. Keep App Secret and access tokens out of code and logs, prefer draft creation by default, preview content on mobile, and require an explicit human approval step before any live publish action.
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
|:-----|:-----|:---------|
| `App ID` | 公众号唯一标识 | 公众号后台 → 开发 → 基本配置 |
| `App Secret` | 公众号密钥 | 公众号后台 → 开发 → 基本配置 |
| `Access Token` | 接口调用凭证 | 通过 API 自动获取 |
### 1.2 可选配置
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
|:-----|:-----|:---------|
| `App ID` | 公众号唯一标识 | 公众号后台 → 开发 → 基本配置 |
| `App Secret` | 公众号密钥 | 公众号后台 → 开发 → 基本配置 |
| `Access Token` | 接口调用凭证 | 通过 API 自动获取 |
### 1.2 可选配置
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
|:-----|:-----|:---------|
| `App ID` | 公众号唯一标识 | 公众号后台 → 开发 → 基本配置 |
| `App Secret` | 公众号密钥 | 公众号后台 → 开发 → 基本配置 |
| `Access Token` | 接口调用凭证 | 通过 API 自动获取 |
### 1.2 可选配置
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
|:-----|:-----|:---------|
| `App ID` | 公众号唯一标识 | 公众号后台 → 开发 → 基本配置 |
| `App Secret` | 公众号密钥 | 公众号后台 → 开发 → 基本配置 |
| `Access Token` | 接口调用凭证 | 通过 API 自动获取 |
### 1.2 可选配置
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
|:-----|:-----|:---------|
| `App ID` | 公众号唯一标识 | 公众号后台 → 开发 → 基本配置 |
| `App Secret` | 公众号密钥 | 公众号后台 → 开发 → 基本配置 |
| `Access Token` | 接口调用凭证 | 通过 API 自动获取 |
### 1.2 可选配置
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
|:-----|:-----|:---------|
| `App ID` | 公众号唯一标识 | 公众号后台 → 开发 → 基本配置 |
| `App Secret` | 公众号密钥 | 公众号后台 → 开发 → 基本配置 |
| `Access Token` | 接口调用凭证 | 通过 API 自动获取 |
### 1.2 可选配置
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
|:-----|:-----|:---------|
| `App ID` | 公众号唯一标识 | 公众号后台 → 开发 → 基本配置 |
| `App Secret` | 公众号密钥 | 公众号后台 → 开发 → 基本配置 |
| `Access Token` | 接口调用凭证 | 通过 API 自动获取 |
### 1.2 可选配置
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
|:-----|:-----|:---------|
| `App ID` | 公众号唯一标识 | 公众号后台 → 开发 → 基本配置 |
| `App Secret` | 公众号密钥 | 公众号后台 → 开发 → 基本配置 |
| `Access Token` | 接口调用凭证 | 通过 API 自动获取 |
### 1.2 可选配置
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
|:-----|:-----|:---------|
| `App ID` | 公众号唯一标识 | 公众号后台 → 开发 → 基本配置 |
| `App Secret` | 公众号密钥 | 公众号后台 → 开发 → 基本配置 |
| `Access Token` | 接口调用凭证 | 通过 API 自动获取 |
### 1.2 可选配置
The sample code retrieves a token by embedding app_id and app_secret directly into a GET query string. Even when functionally correct, this pattern can expose secrets through application logs, proxies, debugging tools, exception traces, and URL capture systems, increasing the chance of credential disclosure.
self.access_token = self._get_access_token()
def _get_access_token(self):
"""获取 Access Token"""
url = f"https://api.weixin.qq.com/cgi-bin/token?grant_type=client_credential&appid={self.app_id}&secret={self.app_secret}"
response = requests.get(url)
return response.json()['access_token']
The README instructs an agent to upload images, create drafts, and publish articles to a WeChat public account, but it does not prominently warn that these are state-changing actions affecting a live user account. In an agent setting, unclear disclosure increases the risk of unintended public posting, account modification, or workflow execution without explicit user consent at the moment of action.
The skill advertises direct and even 'one-click' publication capabilities, including immediate publish operations, but does not require an explicit user confirmation step at the point of execution. In an agent context, this creates a real risk of unintended irreversible actions such as publishing unreviewed, incorrect, or policy-violating content to a live public account.
The entire skill file is written in Chinese and presents itself as a general-purpose markdown syntax reference, but it does not state that the content is intentionally region- or language-specific, nor does it offer an alternative language or user opt-in. Under the policy, forcing a specific language without user choice is a natural-language locale violation.
This markdown file presents all instructions and templates exclusively in Chinese, and it does not indicate that the skill is region-specific or that users may opt into another language. Under the policy rule for natural-language constraints, forcing a specific language without opt-in is a locale-policy concern.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -X GET "https://api.weixin.qq.com/cgi-bin/token?grant_type=client_credential&appid={APPID}&secret={APPSECRET}"
响应示例：
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -X GET "https://api.weixin.qq.com/cgi-bin/token?grant_type=client_credential&appid={APPID}&secret={APPSECRET}"
响应示例：
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -X GET "https://api.weixin.qq.com/cgi-bin/token?grant_type=client_credential&appid={APPID}&secret={APPSECRET}"
响应示例：
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -X GET "https://api.weixin.qq.com/cgi-bin/token?grant_type=client_credential&appid={APPID}&secret={APPSECRET}"
响应示例：
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -X GET "https://api.weixin.qq.com/cgi-bin/token?grant_type=client_credential&appid={APPID}&secret={APPSECRET}"
响应示例：
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -X GET "https://api.weixin.qq.com/cgi-bin/token?grant_type=client_credential&appid={APPID}&secret={APPSECRET}"
响应示例：
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -X GET "https://api.weixin.qq.com/cgi-bin/token?grant_type=client_credential&appid={APPID}&secret={APPSECRET}"
响应示例：
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -X GET "https://api.weixin.qq.com/cgi-bin/token?grant_type=client_credential&appid={APPID}&secret={APPSECRET}"
响应示例：
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -X GET "https://api.weixin.qq.com/cgi-bin/token?grant_type=client_credential&appid={APPID}&secret={APPSECRET}"
响应示例：
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -X GET "https://api.weixin.qq.com/cgi-bin/token?grant_type=client_credential&appid={APPID}&secret={APPSECRET}"
响应示例：
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -X GET "https://api.weixin.qq.com/cgi-bin/token?grant_type=client_credential&appid={APPID}&secret={APPSECRET}"
响应示例：