Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward financial-data query guide that sends user queries to a disclosed external API using a user-provided API key.
Install only if you are comfortable sending financial query text to the disclosed Meixiang/Eastmoney API endpoint. Treat MX_APIKEY as a secret: do not commit it, paste it into shared logs, or expose it in screenshots. Prefer specific queries to avoid large responses, and review any saved mx_data_result.json file before sharing a workspace.
The natural-language description, instructions, warnings, and examples are all presented in Chinese, which can impose a language requirement on users without opt-in. The policy allows locale constraints when explicitly offered as a choice or clearly justified as region-specific, but this file does not provide such an option or justification.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
2. **发送 POST 请求**：
```bash
curl -X POST \
--location 'https://mkapi2.dfcfs.com/finskillshub/api/claw/query' \
--header 'Content-Type: application/json' \
--header "apikey:${MX_APIKEY}" \
This markdown file explicitly tells users to obtain an API key and export it as MX_APIKEY, but it does not mention that the key is sensitive, should be kept secret, or should not be exposed in logs, shared shells, or checked into files. Under the markdown criteria for missing user warnings, credential-handling guidance is relevant because the skill behavior depends on sensitive authentication data.
No suspicious patterns detected.