ClawHub

Route Assistant

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed route-planning skill with no executable code; its main cautions are broad activation words and sharing route details with Amap when used.

Install it if you want route-planning assistance and are comfortable with route queries potentially being processed through Amap. Be cautious with private home, workplace, medical, or sensitive itinerary locations, and expect the skill may respond best to Chinese or bilingual route requests.

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 (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger list contains very broad terms such as "地址", "哪里", "route", and "distance", which are common in everyday conversation and can cause the skill to activate outside its intended scope. Unintended invocation can route unrelated user queries into this skill, causing incorrect handling, unnecessary API usage, privacy exposure of location-related input, and denial of access to the more appropriate skill.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The description says the skill 'automatically recognizes place names and travel routes' but does not define clear invocation boundaries, user consent, or trigger conditions. Broad activation language can cause the agent to engage in unintended contexts, increasing the chance of processing location-related user content when the user did not explicitly request route assistance.

Natural-Language Policy Violations

Medium
Confidence
80% confidence
Finding
The description is written to enforce Chinese-language behavior ('智能出行路线助手') without indicating that the user opted into Chinese responses. Forcing a language can cause misalignment with user intent, reduce transparency, and in multi-skill routing contexts may lead the system to select this skill based on language assumptions rather than an explicit user request.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal