ClawHub
Back to skill

Security audit

ninebot-skill

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language Ninebot device help skill whose device-control guidance is disclosed and purpose-aligned, though users should treat reset and configuration commands carefully.

Before installing, confirm you are comfortable with a skill that may guide changes to Ninebot device settings. Use extra care with factory reset, firmware-related steps, speed limits, and other configuration changes, and require explicit confirmation before applying them to a real vehicle.

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
92% confidence
Finding

The skill exposes potentially destructive operations such as factory reset and parameter modification, but the documentation does not clearly warn about data loss, safety implications, or the need for explicit user confirmation before invoking them. In a device-control skill for vehicles, ambiguous or under-warned commands can lead to unsafe configuration changes, loss of settings, or disruption of device availability.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

All invocation phrases and command examples are specified only in Chinese, with no indication that other languages are supported or that the skill is intentionally restricted to Chinese-speaking users. Under the language/locale policy, a skill should not force a specific language unless it offers user choice or clearly documents and justifies the locale constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.