ClawHub
Back to skill

Security audit

流量重组洗稿虾

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed text-rewriting skill with copyright-adjacent use risks, but it does not show hidden access, persistence, credential use, networking, or destructive behavior.

Install only if you want help rewriting and adapting text. Be careful with copyrighted, confidential, or platform-sensitive material: low estimated duplication does not guarantee permission to publish, originality, or compliance with platform rules.

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
91% confidence
Finding
The trigger list contains broad phrases such as '改写', '换个角度', and '内容改编', which can match many ordinary writing requests and cause the skill to activate unintentionally. In this skill's context, accidental invocation is more concerning because it is explicitly designed to help users preserve '爆款基因', reduce duplication, and '洗稿', which can steer benign requests toward copyright-evasion or policy-evasion workflows.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.