ClawHub
Back to skill

Security audit

文心审

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese academic-paper review assistant with no executable code, persistence, or hidden data handling.

Install if you want a structured Chinese humanities-paper reading aid. Be mindful that when you give it a local PDF path or URL, the agent may read that document or fetch that page as part of the review.

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 (1)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill’s trigger conditions are broad and include common phrases like 'review' and '批评', which can cause the skill to activate in contexts unrelated to deep academic paper analysis. Over-broad activation can lead to unintended data access actions such as reading local PDF paths or fetching arbitrary URLs when the user did not clearly intend to invoke this skill.

Static analysis

No suspicious patterns detected.