ClawHub
Back to skill

Security audit

Xiaohongshu Suggest Keywords

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple browser-based keyword suggestion collector for Xiaohongshu, with the main consideration that searched keywords are sent to that external site.

Install only if you are comfortable having entered keywords sent to Xiaohongshu through a browser session. Avoid using confidential product plans, client names, investigations, or other sensitive terms, and be aware that login state, captchas, and site tracking may affect use.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to type user-provided keywords into Xiaohongshu via browser automation, which transmits those terms to an external third-party service, but it does not warn users about that data disclosure. This is dangerous because users may provide sensitive business, personal, or investigative terms assuming local processing, causing unintended privacy leakage to the target website and any associated tracking or logging systems.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.