ClawHub

Vocab Voyage Mcp

Security checks across malware telemetry and agentic risk

Overview

This is a coherent hosted vocabulary-learning MCP skill, with normal optional token use and analytics that users should understand before enabling authenticated features.

Safe to install for normal vocabulary and test-prep use. Use anonymous mode unless you need personalized features; if you add a personal token, treat it like a password, choose only needed scopes, keep it out of source control, and revoke or rotate it if exposed. Be aware that hosted tool calls may be logged with referral/source attribution and account or IP-derived analytics.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The README instructs users to place a long-lived bearer token directly into a local JSON config file, but does not warn that this stores credentials in plaintext on disk. Plaintext tokens in config files are commonly exposed through local compromise, backups, screenshots, support bundles, or accidental commits, and the token grants access to MCP and potentially user profile/progress scopes.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The document explicitly instructs distributors to append a referral identifier and states that the server records this on every tool call, but it provides no corresponding user-facing disclosure, consent mechanism, or retention/privacy guidance. This creates a privacy and transparency issue because usage can be attributed across channels for authenticated and anonymous clients, and the included analytics query references user_id and ip_hash-derived telemetry.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal