ClawHub
Back to skill

Security audit

SEO内容写作套装

Security checks across malware telemetry and agentic risk

Overview

This is a low-risk SEO writing helper made only of markdown instructions, with no evidence of code execution, persistence, credential access, or destructive behavior.

This appears safe to install as a writing helper. Invoke it deliberately for SEO content tasks, and review generated content for accuracy, originality, language fit, and publishing compliance 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 trigger condition '发送包含技能名称或相关指令的消息即可触发' is overly broad because 'related instruction' is undefined and can cause the skill to activate on loosely matching user input. In an agent environment, ambiguous activation increases the chance of unintended invocation, misrouting, or prompt-surface expansion, especially when the skill can make API calls.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.