ClawHub
Back to skill

Security audit

tock-mcp

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed, read-only Tock restaurant and reservation lookup integration, though it relies on an external MCP package, browser extension, and signed-in Tock session.

Install only if you trust the tock-mcp package and fetchproxy extension. Expect it to read Tock pages through your signed-in browser tab and, for account tools, return profile and reservation details; booking and payment remain outside the MCP tools.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

MCP Config Access

High
Category
Agent Snooping
Content
### 1. Install the MCP server

Add to `.mcp.json` in your project or `~/.claude/mcp.json`:

```json
{
Confidence
95% confidence
Finding
Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.