Back to skill

Security audit

快递查询demo

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward KuaiDi100 package-tracking helper that sends user-provided shipment data to the disclosed courier API.

Install only if you are comfortable sending tracking numbers, carrier codes, and any provided phone-number suffix to KuaiDi100 using your own API credentials. The reviewed files do not show hidden persistence or unrelated data access.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill documentation instructs users to send tracking numbers and optionally the last four digits of a phone number to the external KuaiDi100 API, but it does not clearly warn that this data leaves the local environment and is transmitted to a third party. This creates a privacy and consent risk because users or downstream agents may unknowingly disclose shipment metadata and partial personal data to an external service.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill sends user-supplied tracking numbers and optional phone data to a third-party API without any visible consent flow, disclosure, or minimization controls. Tracking numbers and associated metadata can be sensitive personal or commercial information, so forwarding them externally without clear user awareness creates a privacy and data-handling risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language content of the skill file is exclusively Chinese, and there is no indication that users may choose another language or that the skill is intentionally restricted to a Chinese-language or region-specific audience. The policy explicitly calls out forced language or locale without user opt-in as a violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

Natural-language strings in comments, usage examples, company labels, and messages are Chinese-specific, and the code does not provide any option for users to select another language or locale. Under the language/locale policy, forcing a specific language without opt-in can be a policy concern unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.