ClawHub
Back to skill

Security audit

huohuo-10agents

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language branding and content-planning assistant skill with no code or sensitive system access.

Reasonable to install if you want a Chinese branding/IP and social-content planning assistant. Review any generated marketing or crisis-PR text before publishing, and be aware the broad trigger wording may make the skill appear in general visibility or reputation questions.

SkillSpector

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

High
Confidence
94% confidence
Finding
The trigger scope is extremely broad: it mandates activation for many common marketing/content terms and even the generic phrase '怎么让更多人知道/认可'. In an agent system, this can cause frequent unintended invocation, overriding user intent or routing unrelated requests into this skill, which is a genuine prompt-routing security and reliability issue.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The skill is defined entirely in Chinese and strongly prescribes a Chinese-language persona/workflow without offering a user-language choice. This can lead to poor alignment with user preferences, unexpected language switching, and reduced transparency, which is a real though lower-severity usability and policy-control risk in multilingual agent environments.

Static analysis

No suspicious patterns detected.