Security audit

Jingdong Redirect

Security checks for vulnerabilities and agentic risk

Overview

This is a small redirect skill that points JD.com shopping requests to another skill and includes clear no-login, no-checkout, and no-payment limits.

Installing this legacy redirect appears low risk. Review the separate `jd-shopping` skill before relying on it, because this package points users there but does not include or audit that target skill. Be aware that generic mentions of `JD` may invoke this redirect unexpectedly.

A.I.G

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

SkillSpector

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 (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The trigger list includes very short and generic terms such as "JD" and broad brand terms like "Jingdong" without any narrowing context or exclusion conditions. This can cause unintended invocation when users mention JD.com casually rather than intending to invoke this redirect skill.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.