ClawHub
Back to skill

Security audit

Segway

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Segway device-control skill whose capabilities are disclosed and aligned with its stated purpose, with some safety cautions users should observe before changing settings or resetting a device.

Before installing, treat reset, speed-limit, lighting, firmware, and other configuration commands as real device-control actions. Confirm the target device, keep the vehicle stopped for parameter changes, back up settings before firmware work, and avoid factory reset unless you understand what settings may be erased.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 configuration changes and a factory reset capability without any explicit warning about data loss, irreversible setting changes, or device safety implications. In a vehicle/device-control context, users could unintentionally reset or misconfigure a Segway device, leading to loss of saved settings, degraded operability, or unsafe behavior if parameters such as speed limits are changed carelessly.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language instructions, commands, and examples are all written in Chinese, which can amount to forcing a specific language without user opt-in. The policy allows locale constraints when they are optional or clearly justified, but no such choice or justification is provided here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.