ClawHub
Back to skill

Security audit

旅行紧急助手

Security checks across malware telemetry and agentic risk

Overview

This appears to be a travel-emergency guidance skill with no evidence of malware, exfiltration, persistence, or privileged local access.

Before installing, consider that emergency travel advice can become outdated or jurisdiction-specific. Use it as a helper for organizing next steps, but verify phone numbers, embassy procedures, medical instructions, and police processes with official local sources in a real emergency.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The example invocations use very broad natural-language phrases such as common travel problems, which can cause the skill to trigger when a user is merely discussing a situation rather than explicitly requesting this skill. In an emergency-assistance context, unintended invocation can misroute the conversation, delay more appropriate tools or responses, and increase confusion during time-sensitive situations.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The scenario keywords are highly generic terms like '生病', '受伤', or '警察', which are common in many unrelated conversations and are insufficiently constrained for safe routing. Because this skill provides emergency guidance, accidental activation could surface stale, incomplete, or context-inappropriate advice at the wrong moment, potentially distracting from jurisdiction-specific emergency handling.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.