ClawHub
Back to skill

Security audit

Computer Task Execution

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill is coherent, but it is broad and includes a WeChat test pattern that could cause an agent to send a real message without clear user confirmation.

Review before installing. Use this skill only for explicit action-execution requests, give narrow instructions, and require confirmation before any send, submit, delete, post, approval, or bulk-change action. Remove or edit the WeChat connectivity-test pattern before use.

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

Medium
Confidence
95% confidence
Finding
The skill description is extremely broad and can match a wide range of ordinary user requests, causing over-invocation of a powerful execution-oriented skill. In context, this is more dangerous because the skill is designed to perform real actions across websites and local applications, so accidental selection could lead to unintended task execution, data modification, or risky automation being chosen when a narrower skill should handle the request.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.