ClawHub
Back to skill

Security audit

Title Structure Analyzer - 标题结构分析

Security checks for vulnerabilities and agentic risk

Overview

This is a simple academic-title analysis skill with no executable code, persistence, external access, or hidden high-impact behavior.

Installers should expect this skill to operate best for Chinese-language academic-title review. It does not appear to add local security risk beyond normal use of a text-only writing aid.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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)

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The skill metadata and content are written entirely in Chinese and describe trigger phrases in Chinese, which can steer interaction language without confirming the user's preference. This is not a classic security flaw, but it can violate user-choice and policy expectations, potentially causing confusion, degraded usability, or unsafe miscommunication if a user expects another language.

Static analysis

No suspicious patterns detected.