ClawHub
Back to skill

Security audit

Ad Creator

Security checks across malware telemetry and agentic risk

Overview

This skill is a self-contained advertising copywriting guide, with only a minor risk that its broad trigger words may activate it in unrelated conversations.

Safe to install for advertising and brand-copy workflows. Be aware it may activate when discussing general brand or optimization topics, and review generated advertising for factual accuracy, exaggerated claims, and legal or platform 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
91% confidence
Finding
The trigger terms 'skill, 优化, 品牌, brand' are very broad and overlap with ordinary user conversation, making the skill likely to activate unintentionally. Overbroad activation can cause prompt/context injection into unrelated tasks, unexpected behavior, and loss of user intent control, which is a genuine security and safety concern for agentic systems.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.