ClawHub
Back to skill

Security audit

Meituan Bike

Security checks for vulnerabilities and agentic risk

Overview

This is a simple informational Meituan Bike guidance skill with no code, credential access, persistence, or high-impact authority.

Installers should understand this skill provides general guidance and formulas, not live pricing or account actions. Users should still rely on the Meituan app for current city pricing, parking zones, billing details, and official dispute handling.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Natural-Language Policy Violations

Low
Confidence
76% confidence
Finding
The skill is written primarily in Chinese and is tightly framed around China's Meituan Bike service, but it does not explicitly offer the user a language choice or state that responses should follow the user's preferred language. That can violate a language/locale policy if the organization expects user language preference rather than a fixed default.

Vague Triggers

Low
Confidence
84% confidence
Finding
This markdown file describes 'Agent 典型用法' in broad natural-language terms such as cost analysis, fee interpretation, and commute planning, but it does not specify concrete trigger phrases, activation scope, or negative examples. In a skill-routing context, these generic use cases could overlap with common transportation or budgeting requests and cause unintended invocation.

Static analysis

No suspicious patterns detected.