Crypto Market Data Skill (No Key Required)

• Outcome: Pass
• Latest audit: Jul 10, 2026 · 4:39 AM UTC
• Version: 1.0.2

Overview

This is a coherent market-data skill, with disclosed network API use and a local token cache that users should understand.

Install only if you are comfortable sending market queries to api.igent.net and caching a temporary provider token in the skill's scripts directory. Do not set API_BASE_URL unless you trust the replacement endpoint, keep the skill directory private, and delete scripts/.token if you want to clear the cached session.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (7)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 74% confidence
• Finding: The skill documentation indicates code-level capabilities involving environment access, yet no permissions are declared. Undeclared capabilities reduce transparency for operators and agents, making it harder to assess what the skill can access and increasing the chance of unintended secret or configuration exposure during execution.

Description-Behavior Mismatch

Low

• Confidence: 83% confidence
• Finding: The manifest claims no API key is needed, but the documentation describes authenticated access via automatically retrieved session tokens. This is a security-relevant inconsistency because users may believe the skill is unauthenticated when it actually performs credential acquisition and token handling behind the scenes.

Intent-Code Divergence

Low

• Confidence: 80% confidence
• Finding: The skill advertises 'zero external dependencies' and only standard libraries, but operation depends on external services for data and token issuance. While not a direct exploit by itself, this misrepresentation can cause unsafe deployment assumptions, such as running the skill in environments that disallow outbound network access or require vendor review.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The documentation says an authentication token is stored locally in a hidden .token file without describing permissions, encryption, lifecycle, or user warning. Locally persisted bearer tokens can be stolen by other local processes, accidentally committed to source control, or reused to impersonate the user until expiry.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The code silently persists an API token to a local .token file with no disclosure, permission hardening, or validation of where the token came from. Storing credentials on disk increases exposure to local compromise, accidental inclusion in archives or repos, and token reuse by other local users or processes.

External Transmission

Medium

• Category: Data Exfiltration

Content

### Authentication
Authentication is handled **automatically** by the internal `api_client.js`. Here is how it works simply:

- **Endpoint**: `GET https://api.igent.net/api/token`
- **Mechanism**:
    1.  **Automatic Retrieval**: The first time you use a tool, it asks the server for a temporary session token.
    2.  **Local Storage**: This token is stored in a hidden `.token` file locally so it can be reused for subsequent requests.

• Confidence: 78% confidence
• Finding: https://api.igent.net/

External Transmission

Medium

• Category: Data Exfiltration

Content

const path = require('path');
const url = require('url');

const BASE_URL = process.env.API_BASE_URL || 'https://api.igent.net/api';
const TOKEN_FILE = path.join(__dirname, '.token');
const USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36';

• Confidence: 75% confidence
• Finding: https://api.igent.net/

VirusTotal

65/65 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.