ClawHub
Back to skill

Security audit

小红书数据分析

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Xiaohongshu market-analysis helper that uses a disclosed API key to query marketing analytics data, with no scripts, persistence, or hidden local access found.

Install only if you trust the provider of the XHS_API_KEY and are comfortable sending Xiaohongshu analysis queries, keywords, brands, creator names, and related marketing context to the analytics API. Avoid submitting confidential campaign plans or regulated personal data unless your organization approves that provider.

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
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The README tells users to supply an API key and states that the skill will automatically retrieve related data, but it does not disclose that prompts or query parameters may be sent to an external service. This creates a transparency and consent problem: users may provide sensitive business questions, brand plans, or target-audience data without understanding that the information leaves the local environment.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill’s invocation scope is broad: it applies whenever users ask about content strategy, influencer selection, or market competition, but it does not define clear exclusions or narrower routing criteria. This can cause the skill to be triggered for loosely related requests, leading the agent to expose or rely on specialized market-analysis behavior when a more appropriate tool or a general response should have been used.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill mandates Chinese output without allowing user preference or locale negotiation. In multilingual environments, this can cause incorrect or inaccessible responses, and may override higher-level system or user language settings in ways that reduce transparency and safe usability.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.