ClawHub

Product

Security checks across malware telemetry and agentic risk

Overview

This skill mainly queries a fore.vip product catalog through a disclosed external API, with no evidence of hidden local access or malicious behavior.

Install only if you are comfortable sending product search terms, tags, and pagination parameters to fore.vip. Keep use scoped to catalog browsing, avoid including secrets or sensitive business queries, and require explicit user confirmation before allowing any create_activity or other write-capable MCP action.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (16)

Description-Behavior Mismatch

Medium
Confidence
91% confidence
Finding
The skill is presented as a product-query skill, but the documentation also advertises `/mcp/create_activity`, which is a state-changing remote action. This scope expansion is dangerous because agents or users may invoke modification capabilities without realizing the skill can create remote records, increasing the chance of unintended actions on an external service.

Description-Behavior Mismatch

Medium
Confidence
89% confidence
Finding
The SEO and notes sections broaden the skill from read-only product querying into product management and activity creation use cases, which materially changes the trust boundary. Mismatched purpose statements can mislead downstream systems, reviewers, and users about whether the skill is safe to run in a read-only context.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The README instructs agents to send requests to an external service but does not warn that user prompts, filters, or other query data may be disclosed to a third-party endpoint. In an agent-skill context, this omission is security-relevant because users may not realize their data leaves the local environment, creating privacy and compliance risk.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
Documenting a create-activity endpoint without any warning about remote side effects can cause an agent to perform unintended writes to a third-party system. In an agent-skill context, silent write operations are especially risky because they may be triggered automatically from user prompts or planning steps.

Missing User Warnings

Low
Confidence
82% confidence
Finding
The skill instructs agents to send requests to an external service but does not disclose that user-provided search parameters and metadata will be transmitted off-platform. This is a privacy and transparency issue rather than an exploit by itself, but it can still expose user data or enterprise query patterns to a third party.

Missing User Warnings

Low
Confidence
95% confidence
Finding
The skill explicitly instructs users to query an external MCP endpoint on api.fore.vip, but it does not warn that user-supplied search terms and metadata are transmitted off-platform. This is a real transparency/privacy issue because agents may forward user queries or business-sensitive product lookups to a third party without informed consent.

External Transmission

Medium
Category
Data Exfiltration
Content
### Basic Product Query

```javascript
const response = await fetch('https://api.fore.vip/mcp/query_kl', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
Confidence
84% confidence
Finding
fetch('https://api.fore.vip/mcp/query_kl', { method: 'POST'

External Transmission

Medium
Category
Data Exfiltration
Content
const limit = 20;
const skip = (page - 1) * limit;

const response = await fetch('https://api.fore.vip/mcp/query_kl', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
Confidence
84% confidence
Finding
fetch('https://api.fore.vip/mcp/query_kl', { method: 'POST'

External Transmission

Medium
Category
Data Exfiltration
Content
## 🔧 MCP Server Configuration

**Endpoint**: `https://api.fore.vip/mcp/query_kl`  
**Method**: `POST`  
**Content-Type**: `application/json`
Confidence
90% confidence
Finding
https://api.fore.vip/

External Transmission

Medium
Category
Data Exfiltration
Content
### Basic Product Query

```javascript
const response = await fetch('https://api.fore.vip/mcp/query_kl', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
Confidence
84% confidence
Finding
https://api.fore.vip/

External Transmission

Medium
Category
Data Exfiltration
Content
const limit = 20;
const skip = (page - 1) * limit;

const response = await fetch('https://api.fore.vip/mcp/query_kl', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
Confidence
84% confidence
Finding
https://api.fore.vip/

External Transmission

Medium
Category
Data Exfiltration
Content
```javascript
// 按标签查询产品
const result = await fetch('https://api.fore.vip/mcp/tools/call', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
Confidence
93% confidence
Finding
fetch('https://api.fore.vip/mcp/tools/call', { method: 'POST'

External Transmission

Medium
Category
Data Exfiltration
Content
this.loading = true
      
      try {
        const response = await fetch('https://api.fore.vip/mcp/tools/call', {
          method: 'POST',
          headers: { 'Content-Type': 'application/json' },
          body: JSON.stringify({
Confidence
93% confidence
Finding
fetch('https://api.fore.vip/mcp/tools/call', { method: 'POST'

External Transmission

Medium
Category
Data Exfiltration
Content
### 调用工具

```bash
curl -X POST https://api.fore.vip/mcp/tools/call \
  -H "Content-Type: application/json" \
  -d '{
    "name": "query_kl",
Confidence
90% confidence
Finding
https://api.fore.vip/

External Transmission

Medium
Category
Data Exfiltration
Content
```javascript
// 按标签查询产品
const result = await fetch('https://api.fore.vip/mcp/tools/call', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
Confidence
93% confidence
Finding
https://api.fore.vip/

External Transmission

Medium
Category
Data Exfiltration
Content
this.loading = true
      
      try {
        const response = await fetch('https://api.fore.vip/mcp/tools/call', {
          method: 'POST',
          headers: { 'Content-Type': 'application/json' },
          body: JSON.stringify({
Confidence
93% confidence
Finding
https://api.fore.vip/

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal