Back to skill

Security audit

慢慢买比价助手

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese shopping price-comparison skill with disclosed commerce guidance and no executable code or hidden data access.

Installers should understand this skill is aimed at Chinese shopping price checks and may provide purchase-timing or CPS rebate-related advice. Verify prices and rebate incentives independently before buying, and review any future version carefully if it adds real reminders, account access, or automated tracking.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list includes broad, common phrases such as '历史价格'、'价格走势'、'比价工具', which can match many ordinary shopping conversations and cause the skill to activate unintentionally. In a commerce-related skill, accidental invocation can misroute user queries, create confusing outputs, and increase the chance of inappropriate affiliate or purchase guidance being injected into unrelated contexts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

文件整体以中文命名、描述和触发词呈现,但未说明该技能是否仅面向中文用户,也未提供语言/locale 选择。按规则,若技能隐含固定语言输出而没有用户选择或合理的地域限定说明,可能构成语言策略问题。

Content

No source excerpt is available for this finding.