ClawHub
Back to skill

Security audit

Xiaohongshu Hotspot Writer1

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches a public hot-topics page and generates Chinese Xiaohongshu-style AI content in chat, with no file writes, execution, persistence, or credential use.

Install this if you want a Chinese AI/tech Xiaohongshu hot-topic copywriting helper. Be aware that a broad request like "帮我写小红书" may route into this AI-hotspot workflow even when you intended a different Xiaohongshu task, and the skill is designed to output Chinese by default.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
94% confidence
Finding
The skill description includes broad trigger examples such as '今日AI热点' and '帮我写小红书', which can plausibly appear in ordinary user conversation and cause unintended activation. Over-broad triggering can route unrelated requests into this skill, leading to unexpected web access and content generation behavior that the user did not explicitly request.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The skill is hard-coded to operate in Chinese and produce Chinese-language output without checking the user's language preference. This can override user expectations, reduce usability, and in multilingual environments may cause the agent to respond in an unintended language, though it is not a direct security compromise.

Static analysis

No suspicious patterns detected.