Back to skill

Security audit

什么值得买价格爬取

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed public price-lookup helper for smzdm.com and does not request local access, credentials, persistence, or destructive actions.

Before installing, be aware that the skill is written for Chinese-language smzdm.com price searches and may activate on broad NAS or brand-related queries. Use it for public price lookup only, avoid excessive scraping, and verify prices on the actual merchant page before buying.

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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description and the entire skill instructions are written exclusively in Chinese, and the usage/output examples assume Chinese-language interaction. There is no statement that the skill supports other languages or that Chinese is a justified region-specific requirement, which can violate language/locale policy expectations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger keywords include broad brand and product terms such as "smzdm", "群晖", and "NAS价格", which can cause the skill to activate for general conversation rather than clear user intent to use this specific scraping skill. This increases the chance of unintended execution, including unnecessary web-scraping behavior or routing user requests to the wrong capability.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The natural-language metadata and all trigger keywords are Chinese-only, which effectively constrains use to one language without any opt-in or justification. Under the policy, language restrictions should either provide user choice or clearly document a justified locale-specific scope.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.