Back to skill

Security audit

China Local Life Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow China local-services comparison skill with explicit limits against logging in, booking, ordering, or paying.

Install this if you want advice comparing China local-life platforms. You should still manually review final prices, availability, coupon terms, and merchant risk, and the agent should not log in, place orders, book travel, or make payments for you.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The user-facing instruction is written as a requirement to input needs using Chinese terms like “外卖、团购、餐厅、打车、酒店、机票、火车票,” which implies a Chinese-language interaction model. The file does not explicitly offer a language choice or state that other languages are also supported, creating a locale/language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description explicitly defines the assistant as a "China local-life flagship assistant" and limits comparisons to China-specific platforms and services. This is a natural-language locale constraint, but the manifest does not indicate user choice, opt-in, or a documented justification that this skill is intentionally region-specific.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.