ClawHub
Back to skill

Security audit

Caixin

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill summarizes public Caixin news pages and does not include code, credential access, persistence, or hidden behavior.

Install only if you want an agent to visit and summarize public Caixin pages. Keep use limited to visible public content, avoid login-only or paid material, and treat any collection as lightweight and compliant with the site’s rules.

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
92% confidence
Finding
The description says the skill should be called whenever access to or automation of Caixin-related content is needed, which is a broad activation trigger. Overly broad routing can cause the agent to invoke this skill in cases where it is unnecessary or inappropriate, increasing the chance of unintended browsing, data handling, or policy-bound scraping behavior.

Natural-Language Policy Violations

Low
Confidence
84% confidence
Finding
The description is written in Chinese and implicitly fixes the skill behavior and presentation to that language context without indicating user choice. Enforcing a language without opt-in can cause user-interface confusion, incorrect routing for users expecting another language, and reduced transparency about what the skill will do.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.