ClawHub

小红书数据分析

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a purpose-aligned Xiaohongshu marketing analysis helper, with privacy and trigger-scope documentation gaps but no evidence of malicious behavior.

Install only if you are comfortable sharing the Xiaohongshu topics, competitors, influencer identifiers, or audience details you ask it to analyze. Avoid entering confidential business plans, private customer data, credentials, or account-only data unless the publisher documents where that data is sent and retained.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The README states that the skill will automatically retrieve related data once the user describes a question, but it does not explain what data sources are queried, what user or third-party data may be sent, or what privacy/compliance implications exist. In a marketing-intelligence skill that analyzes influencers, competitors, and audience profiles, this omission can lead users to unknowingly submit sensitive business data or trigger collection/processing of personal or platform-derived data without informed consent.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger conditions are very broad and cover common Xiaohongshu analysis intents such as note analysis, competitor benchmarking, algorithm understanding, and optimization. This increases the chance of unintended invocation, causing the wrong skill to activate for loosely related requests and potentially leading to scope confusion or unsafe routing, especially because the metadata also includes many generic trigger phrases.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal