ClawHub
Back to skill

Security audit

Text Diff Be5bd0

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language learning note for React/text diff concepts and does not request sensitive access or perform actions.

Before installing, expect a lightweight Chinese-language learning aid with broad text-diff triggers and limited practical depth; there is no indication it will run code, access private data, or change your environment.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill metadata and content are entirely in Chinese and implicitly constrain activation and use to Chinese-language phrasing without documenting user choice, fallback behavior, or language negotiation. While not directly dangerous like code execution, this can cause misrouting, exclusion of non-Chinese users, and unintended behavior if the agent applies the skill without confirming the user's preferred language.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger condition '用户需要text-diff相关帮助' is overly broad and can activate the skill for generic requests about text diffing rather than an explicit invocation. This increases the chance of unintended routing, causing the agent to apply this loosely defined skill in contexts the user did not intend, which can degrade response quality and create prompt-scope confusion.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.