Back to skill

Security audit

越野纵横 China Offroad

Security checks for vulnerabilities and agentic risk

Overview

This is a China off-road trip-planning skill with disclosed web-checking and safety guidance, and no code, persistence, credential handling, or hidden execution behavior.

Install this if you want Chinese-language China off-road and self-drive planning. Treat its route, permit, weather, and restaurant details as starting points and verify official local notices before travel; be aware it may activate on some broader road-trip questions and answer in Chinese by default.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation text is extremely broad and includes generic travel, route-planning, dining, and sightseeing intents such as asking where to go or what to eat along the way. This can cause the skill to hijack unrelated requests and inject off-road-specific assumptions or advice into contexts where the user did not ask for it, reducing routing integrity and potentially surfacing unsafe guidance in normal travel scenarios.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

Mandating Chinese-only output without checking the user's preferred language can exclude users, distort safety-critical instructions through forced localization, and interfere with platform-level language handling. In a skill that provides route, compliance, and emergency-oriented guidance, inability to communicate in the user's language can increase misunderstanding risk.

Content

No source excerpt is available for this finding.