ClawHub
Back to skill

Security audit

test

Security checks across malware telemetry and agentic risk

Overview

This is a content-only Douyin marketing advice skill with no code, installs, credentials, or privileged actions.

Safe to install for Douyin marketing and livestream strategy help. Treat platform, advertising, and compliance advice as guidance to verify against current Douyin rules and applicable law, and review future versions carefully if they add executable code, installs, credentials, or account access.

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
88% confidence
Finding
The activation guidance is overly generic: referencing the agent by name or broad specialty can cause the skill to trigger in situations where the user did not explicitly request this specialized behavior. In an agent framework, this can lead to unintended routing, unexpected persona takeover, or injection of domain-specific assumptions into unrelated tasks.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.