ClawHub
Back to skill

Security audit

Meituan

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small Meituan browsing aid for public merchant and coupon information, with no bundled code, persistence, credential handling, or hidden execution.

Install only if you want help analyzing public Meituan pages. Do not use it for ordering, account actions, private data, scraping at scale, or bypassing Meituan controls; verify prices, availability, and region-sensitive details at the time of use.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger description is broad enough to capture a wide range of Meituan-related requests, which can cause the skill to activate in contexts the user did not explicitly intend. Over-broad routing increases the chance of unintended browsing or automation on a third-party site, especially for requests that only mention Meituan incidentally.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill content is entirely in Chinese and frames operation around Chinese-language usage without any indication that language should follow user preference. This can lead to unintended language switching, reduced transparency, and user confusion, which is a safety and usability issue when the agent acts on behalf of a user.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.