ClawHub
Back to skill

Security audit

Content Research Writer Cn

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only writing and research helper whose capabilities match its stated purpose.

Safe to install for writing support. Verify researched facts and citations before publishing, and only provide drafts, sources, or writing samples you are comfortable using in the session.

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
86% confidence
Finding
The Chinese trigger phrases listed in the description (e.g. terms equivalent to 'write article', 'content creation', 'copywriting', 'blog') are broad, generic phrases likely to appear in normal user conversation. This can cause unintended skill activation, routing user requests into a skill context they did not explicitly choose, which is a prompt-selection and UX safety issue rather than code execution.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.