Back to skill

Security audit

多平台快递查询

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese courier-tracking helper; it uses tracking numbers with carrier or aggregator websites, which users should expect but should still treat as a privacy disclosure.

Install this if you are comfortable sharing package tracking numbers with courier sites or aggregators such as kuaidi100. Avoid providing extra verification details like phone-number suffixes or login information unless you understand which official site is requesting them, and double-check results when postal-carrier identification matters.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (11)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The invocation examples are generic everyday phrases like '帮我查一下快递' and '快递到哪了', which can cause the skill to activate unintentionally in normal conversation. This increases the chance that users disclose tracking numbers or trigger third-party lookups without clear intent, creating privacy and consent risks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill directs the agent to query third-party services such as kuaidi100 and carrier websites, but it does not warn users that their tracking number will be transmitted to external websites and browser tools. Tracking numbers can be sensitive identifiers tied to a person's purchases, address, or delivery activity, so silent disclosure undermines user privacy and informed consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The instruction explicitly requires output formatting using Chinese punctuation and the document is written to enforce Chinese responses without any opt-in or alternative language path. This is a natural-language policy concern because it forces a specific language/locale rather than offering user choice or documenting a justified region-specific limitation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

This JSON manifest encodes all descriptions, carrier names, apps, and matching keywords exclusively in Chinese, with no indication that users can opt into another language or locale. Because SQP-3 applies to all file types and covers forced language/locale behavior, this appears to hard-code a single language context without documented choice.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document’s stated postal-carrier rules and the pseudocode diverge, which can cause the skill to misidentify postal tracking numbers or fail to recognize valid ones. In a logistics-identification skill, inconsistent logic is dangerous because downstream lookups, user guidance, or automated routing decisions may rely on the documented behavior and produce incorrect results.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This code file contains user-facing natural-language text and documentation exclusively in Chinese, including the script description and later CLI output. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The entire skill documentation is written in Chinese and does not indicate that other languages are supported or that Chinese is a locale-specific requirement. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire skill-related test document is written only in Chinese, with no indication that users may choose another language or that the skill is intentionally restricted to a Chinese-only regional use case. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file is written entirely in Chinese and presents all instructions, examples, and labels only in that language. Under the policy, forcing a specific language without offering a user language choice or documenting a justified locale restriction is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The postal tracking regex/example section conflicts with later identification rules, indicating the skill may teach one format while implementing another. This inconsistency can mislead users and cause false matches or missed matches, though the impact is limited to classification accuracy rather than direct code execution or privilege compromise.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This code file contains user-facing natural-language content such as the module description and output labels entirely in Chinese. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation when no alternative language or justification is provided.

Content

No source excerpt is available for this finding.