ClawHub
Back to skill

Security audit

内容工坊

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed content-generation workflow that uses web search for current topics and does not include hidden code, persistence, credential access, or destructive behavior.

Install this if you want a Chinese-language workflow for generating and adapting self-media content. Review generated drafts before publishing, especially facts from current-event searches, and be aware that broad prompts about what to write may invoke 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

Medium
Confidence
89% confidence
Finding
The trigger phrases include very broad, everyday requests such as '今天写什么' and '帮我生产本周内容', which can match ordinary conversation and cause unintended skill activation. In an agent system, over-broad activation can redirect user requests into web-search-driven content generation without clear intent, increasing the risk of surprise tool use, irrelevant actions, or accidental data exposure through unnecessary processing.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.