ClawHub

标书服务

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese bid-document advice skill that openly promotes a related website and group QR code, with no executable code or hidden access.

Install this only if you are comfortable with a Chinese-language bid assistant that may point you to biaoshu.supcon.com and a WeCom QR-code group. Do not share confidential tender documents, pricing, credentials, client details, or internal project information with the external site, group, or web search unless your organization has approved it.

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
88% confidence
Finding
The trigger condition is very broad: any mention of bid-related information can activate the skill, which increases the chance of unsolicited promotional behavior and accidental invocation outside the user's actual intent. In this skill, broad activation is coupled with mandatory promotion of an external website and QR code, making it more likely the agent will redirect users to third-party resources when they only asked for neutral informational help.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
Mandating Chinese-only output without user opt-in can override user preferences and reduce transparency, especially for multilingual users who may not understand the response or the external links being promoted. While not directly a code-execution issue, it weakens user control and can facilitate unwanted redirection or misunderstanding in security-sensitive contexts.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal