ClawHub
Back to skill

Security audit

Top Brand Core Builder(顶级品牌内核构建)

Security checks across malware telemetry and agentic risk

Overview

This is a local Chinese brand-strategy skill with aggressive persuasion framing, but I found no evidence of data theft, persistence, credential use, or automatic external actions.

Install only if you want a Chinese-language branding framework that uses strong persuasion concepts such as dependency, emotional connection, and decision-path control. Review generated strategy before using it publicly, avoid unsupported or manipulative claims, and expect at least one included script to need a bug fix for reliable CLI 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 (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The activation condition is very broad: it says to use the skill whenever a user wants to create a new brand, upgrade an existing brand, or design brand strategy, which can match a large share of ordinary business requests. Over-broad triggering can cause the agent to invoke this persuasive, strategy-shaping skill in situations where the user did not explicitly ask for it, increasing the chance of unwanted steering or inappropriate tool selection.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The skill is written entirely in Chinese and does not offer a language-choice mechanism or document a legitimate locale constraint. In multilingual environments, this can cause the agent to respond in an unexpected language, reducing user comprehension and making it harder to detect manipulative framing in a skill already focused on influencing decisions.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.