ClawHub
Back to skill

Security audit

jp-device-skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language placeholder for JinPeng vehicle assistance and does not include executable code or actual vehicle-control integration.

Installing this should only add a placeholder response for JinPeng vehicle queries. Before relying on a future version that connects to vehicles, check that it clearly asks permission for location/trip data and confirms any setting changes such as speed limits.

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
86% confidence
Finding

The skill advertises access to sensitive vehicle telemetry and the ability to change vehicle parameters such as speed limits, but it provides no warning, consent model, authorization boundaries, or safety constraints. In a vehicle context, silent access to location/battery/trip data and silent modification of operating parameters can create privacy risks and unsafe system-impacting behavior if the skill is later implemented as described.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

All natural-language content in the skill is presented only in Chinese, and the fixed output is also mandated in Chinese without any opt-in or language choice. Under the policy, forcing a specific language without user choice can be a locale-policy violation unless the restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.