Security audit

Jd Express Tracker

Security checks for vulnerabilities and agentic risk

Overview

This JD package-tracking skill is mostly purpose-aligned, but it asks for a live JD session token and stores recent waybill numbers without clear privacy controls.

Review this before installing if you are concerned about privacy: the skill may send JD waybill numbers and a JD session token to JD endpoints, and its documentation tells callers to keep a local recent-history cache. It should add clear token-handling rules, remove unnecessary headers, and either disable or tightly control cached waybill history.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (3)

T09 · Insecure Skill Coding Practices

Warning

Location: skills/jd-express-tracking/SKILL.md:36
Finding: Undisclosed Retention of Sensitive Waybill Identifiers
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: skills/jd-express-tracking/references/api-spec.md:27
Finding: Overbroad Request Headers Expose or Spoof Network and Device Metadata
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: skills/jd-express-tracking/references/api-spec.md:62
Finding: Ambiguous Authentication Rules May Expose a Reusable JD Session Token
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (7)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The manifest description, title, and usage examples are entirely in Chinese and present the skill as operating in that language by default. Under the policy, language constraints should either offer user choice or be clearly justified as region-specific; this file does not state such a justification or opt-in.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The trigger list includes broad phrases such as ‘查快递’, ‘快递查询’, and ‘运单号’, which are common across many logistics contexts and can cause this skill to activate for unrelated courier requests. In this skill, misrouting is more concerning because it may lead the agent to request or process sensitive tracking numbers unnecessarily, and the workflow also references alternate order-query behavior when no waybill is provided, increasing the chance of unintended tool routing.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The document explicitly requires a live JD session token in the js-token header but provides no warning about secure handling, storage, or transmission of that credential. In an agent skill context, documenting a session token as a required input without guardrails increases the chance that implementers or downstream tools will collect, log, persist, or misuse a bearer-like credential that can expose a user's logistics/account context.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The skill requires sending a JD session token and user-supplied waybill queries to external JD endpoints, but it does not explicitly warn that user data and authentication material leave the local environment. This creates a transparency and privacy issue: users or integrators may unknowingly transmit tracking data to a third party and mishandle token usage.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill instructs the caller to cache recent waybill codes locally but provides no guidance on retention, access controls, or user privacy. Tracking numbers can be linked to shipment activity and potentially to individuals, so undocumented local storage increases privacy and data-handling risk even if the data is not highly sensitive by itself.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 76% confidence
Finding: The reference hard-codes accept-language to prioritize zh-CN, which reflects a locale preference. The file does not indicate that this locale is user-selectable or justified as a region-specific requirement, so it may conflict with language/locale choice policy.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The specification states that queried waybill codes are written to local storage and retained as recent history, but gives no notice, retention policy, or control to the user. Waybill numbers are sensitive tracking identifiers that can reveal shipment activity and, when correlated with other data, may expose personal behavior or order relationships.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.