ClawHub
Back to skill

Security audit

引流裂变

Security checks across malware telemetry and agentic risk

Overview

This is a simple planning guide for viral-growth campaigns and does not contain code or ask for account access.

This skill is reasonable to install as a planning aid. Before using its advice in a real campaign, confirm the applicable jurisdiction, platform rules, privacy requirements, data-minimization approach, and human approval process, especially if personal data or regulated outreach is involved.

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 invocation description is broad enough that the skill may be triggered for many general growth, operations, or marketing tasks beyond the user's intent. This can cause unintended activation, leading the agent to apply domain-specific guidance inappropriately and increasing the chance of privacy, compliance, or business-process mistakes in sensitive outreach workflows.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal