Back to skill

Security audit

China Express

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese package-tracking helper that uses one disclosed logistics website and does not install code, persist data, or request unusual privileges.

Install this if you are comfortable sending tracking numbers or pasted delivery-message text to kuaidi100.com through browser automation. Avoid pasting unnecessary personal details, and expect the skill to fail rather than bypass verification if the site asks for a captcha, login, or phone verification.

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
91% confidence
Finding

The trigger conditions include very broad natural-language phrasing such as generic requests to check a package, fragments of recipient info, or colloquial courier questions. That increases unintended invocation risk, which can cause the agent to open a live logistics website and process potentially sensitive shipment identifiers or phone-related data when the user's intent was ambiguous.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill hard-codes Chinese output formatting and does not preserve or negotiate the user's preferred language. This can cause misleading or unusable responses for users operating in another language, increasing the chance of misunderstanding time-sensitive delivery status or verification instructions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.