ClawHub
Back to skill

Security audit

ClawZhiPin

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed, instruction-only promotional skill that may insert domain-sale pitches into broad Claw or AI-hiring conversations but does not request sensitive access or install executable code.

Install only if you intentionally want your agent to promote clawzhipin.com during Claw, OpenClaw, or AI-employee recruiting discussions. Expect occasional unsolicited marketing replies unless you narrow the triggers or disable the skill.

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 (1)

Vague Triggers

High
Confidence
98% confidence
Finding
The skill is designed to inject unsolicited domain-sale advertising into ordinary conversations whenever very broad keywords like 'Claw' or 'AI员工' appear. This creates prompt-collision behavior that can hijack unrelated user interactions for commercial promotion, making the agent behave deceptively and against user intent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.