ClawHub
Back to skill

Security audit

Ninebot

Security checks for vulnerabilities and agentic risk

Overview

This is a small Chinese-language Ninebot guidance skill with disclosed device diagnostics and configuration behavior, and no bundled code or hidden execution path.

Before installing, understand that this skill may guide an agent through Ninebot configuration actions such as changing speed limits or factory reset. Use it only when you control the device, confirm any reset or configuration write explicitly, and consider safety, pairing, warranty, and local regulatory effects.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill documents state-changing and potentially destructive operations such as parameter modification and factory reset, but it does not warn about data loss, safety implications, or the need for explicit user confirmation before applying changes. In the context of vehicle-like devices, changing speed limits or resetting configuration can affect safe operation, device pairing, and recoverability, so omission of warnings meaningfully increases the chance of harmful misuse.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The listed invocation phrases and examples are entirely in Chinese, and the document does not indicate whether other languages are supported or whether the skill is intentionally limited to Chinese-speaking users. For natural-language policy review, forcing a specific language without user opt-in or documented justification can be a locale-policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.