Security audit
Security checks for vulnerabilities and agentic risk
This is a troubleshooting guide for a DeepSeek API compatibility bug, with no hidden install steps, persistence, or unrelated data access.
Install only if you are comfortable using a Chinese-language troubleshooting guide. If you run the reproduction snippet, use test prompts and test tool outputs rather than private user data or production credentials.
The manifest description and the instructional content are presented in Chinese, and the file does not indicate that the user can choose another language or that the skill is region- or locale-specific. This can violate language/locale policy because it effectively forces a specific language without user opt-in.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
import requests
# 1. 首次请求（带 thinking + tool calls）
response = requests.post("https://api.deepseek.com/v1/chat/completions", json={
"model": "deepseek-v4-pro",
"reasoning": {"effort": "low"},
"messages": [
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
import requests
# 1. 首次请求（带 thinking + tool calls）
response = requests.post("https://api.deepseek.com/v1/chat/completions", json={
"model": "deepseek-v4-pro",
"reasoning": {"effort": "low"},
"messages": [
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
import requests
# 1. 首次请求（带 thinking + tool calls）
response = requests.post("https://api.deepseek.com/v1/chat/completions", json={
"model": "deepseek-v4-pro",
"reasoning": {"effort": "low"},
"messages": [
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
import requests
# 1. 首次请求（带 thinking + tool calls）
response = requests.post("https://api.deepseek.com/v1/chat/completions", json={
"model": "deepseek-v4-pro",
"reasoning": {"effort": "low"},
"messages": [
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
import requests
# 1. 首次请求（带 thinking + tool calls）
response = requests.post("https://api.deepseek.com/v1/chat/completions", json={
"model": "deepseek-v4-pro",
"reasoning": {"effort": "low"},
"messages": [
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
import requests
# 1. 首次请求（带 thinking + tool calls）
response = requests.post("https://api.deepseek.com/v1/chat/completions", json={
"model": "deepseek-v4-pro",
"reasoning": {"effort": "low"},
"messages": [
No suspicious patterns detected.