ClawHub

x2c-real-dashboard

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed X2C dashboard helper that uses a user-provided API key to fetch private account metrics, with no evidence of hidden or destructive behavior.

Install only if you trust this X2C integration with read access to your dashboard. Store X2C_API_KEY as a secret, avoid committing config files containing it, and be careful sharing outputs because they may include earnings, transactions, and project performance data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill invokes shell scripts but does not declare corresponding permissions, creating a transparency and governance gap between what the skill claims and what it can actually do. In a credentialed skill that reads X2C_API_KEY and queries private dashboard data, undeclared shell capability increases the chance of unreviewed command execution paths and weakens user/admin ability to assess risk.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill description does not warn users that it accesses the sensitive X2C_API_KEY and retrieves private financial and transaction data from a personal dashboard. This can lead to uninformed use of a high-sensitivity skill, causing accidental disclosure of earnings, transaction history, or other private account information to the agent workflow or downstream surfaces.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The script silently sends a POST request to an external Supabase endpoint using an API credential from the environment, with no user-facing notice or consent mechanism. In an agent skill context, undisclosed outbound transmission of dashboard queries and authenticated access is a real privacy and trust concern, even if the destination appears related to the stated service.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal