ClawHub
Back to skill

Security audit

Tmp.XuBXJbJg0f

Security checks across malware telemetry and agentic risk

Overview

This skill is a clearly disclosed OpenTable reservation helper, but users should understand it can act on their real signed-in OpenTable session.

Install only if you are comfortable letting an MCP tool use your signed-in OpenTable browser session. Review the npm package and fetchproxy extension you install, and require explicit confirmation before booking, modifying, canceling, or changing favorites, especially where cancellation policies or saved-card no-show fees are involved.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger description ends with a broad catch-all phrase covering 'any request involving OpenTable restaurant reservations,' which can cause the skill to activate on ambiguous user intents. Because this skill can perform live account actions such as booking, canceling, and modifying reservations through an authenticated browser session, over-broad activation increases the chance of unintended invocation and downstream account changes.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The description says the skill can manage reservations and favorites but does not clearly warn that these are live, state-changing operations against the user's real OpenTable account. In this context, the skill operates through a signed-in browser tab and exposes booking, cancellation, modification, and favorites management, so insufficient disclosure can mislead users into authorizing actions with real-world consequences.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.