Back to skill

Security audit

比货购物助手

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese shopping comparison skill with no executable code, persistence, or hidden high-impact behavior.

Installers should understand that this skill is written for Chinese shopping-comparison interactions. Narrower trigger phrases would reduce accidental activation, but the artifact does not show hidden code, credential handling, persistence, or destructive behavior.

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
  • 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

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill name, description, and trigger phrases are entirely Chinese-centric, with no indication that other languages are supported or that the Chinese-only behavior is an intentional, justified regional constraint. This can violate language/locale policy when users are not given an explicit language choice or opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list contains broad everyday phrases such as '哪个好', '买哪个', '商品比较', and '产品对比', which can match many normal conversations and cause unintended invocation. In a shopping-assistant context this is not directly code-execution dangerous, but it can misroute user requests, create privacy concerns if unrelated shopping queries are captured, and degrade agent reliability.

Content

No source excerpt is available for this finding.