ClawHub
Back to skill

Security audit

zayn-complaint

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese complaint-analysis prompt skill that asks for relevant aftersales evidence but contains no code, install hooks, persistence, or hidden actions.

Before installing, confirm this skill will be used only with authorized complaint data. Provide the minimum necessary order, product, evidence, and warranty details, redact unrelated personal information where possible, and keep final refund, replacement, compensation, or legal decisions with authorized staff.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly requests and prioritizes sensitive operational and customer-linked data such as order details, serial numbers, images/videos, shipping/signature records, and historical aftersales records, but it does not include any privacy notice, data-minimization rule, or handling restrictions. This creates a real risk of unnecessary collection, overexposure, or downstream misuse of personal or sensitive business data during complaint handling.

Natural-Language Policy Violations

Medium
Confidence
87% confidence
Finding
The examples and invocation template are entirely in Chinese and provide no indication that users may interact in another language or request localization. This can exclude or mislead non-Chinese-speaking users, causing incorrect complaint intake or loss of important evidence details, though it is not a direct security exploit.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.