ClawHub
Back to skill

Security audit

Daily Hot Deals

Security checks across malware telemetry and agentic risk

Overview

This is a low-risk local deal-report skill, though its documentation advertises WeChat delivery and scheduled pushes that are not implemented in the included code.

Installing the current artifact should only provide a local sample report generator. Before enabling any future WeChat delivery, paid subscription, live deal aggregation, or scheduled push feature, check that it clearly explains what account identifier and report data are sent, when it sends, and how to disable it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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)

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The skill explicitly offers to send reports to WeChat but provides no privacy notice, consent flow, or explanation of what user data would be transmitted to a third party. In a commerce-oriented skill, this can expose identifiers, preferences, subscription behavior, or message contents without informed user consent, creating avoidable privacy and compliance risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.