ClawHub
Back to skill

Security audit

Tokei Agent

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Tokei campaign-management CLI/MCP tool with expected API access, but users should handle participant data and write-capable keys carefully.

Install only if you intend to let an agent or CLI access your Tokei account. Prefer a read-only API key for monitoring, use read+write keys only for tasks that modify campaigns, entries, or webhooks, and avoid pasting or exporting participant records unless necessary.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill clearly performs network operations against the Tokei REST API and even exposes an MCP server that can trigger those calls, yet it declares no explicit permissions beyond environment requirements. That mismatch weakens transparency and policy enforcement, making it easier for users or hosting platforms to underestimate the skill’s ability to transmit data off-host and manipulate remote resources.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The skill provides commands that enumerate entries, survey responses, and leaderboard data, which can expose participant emails and other potentially sensitive campaign data, but it does not prominently warn users about that privacy risk. In an agent context, this increases the chance of unnecessary collection, display, or onward transmission of personal data during routine use.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.