JD商品评价

• Outcome: Review
• Latest audit: May 29, 2026 · 9:36 PM UTC
• Version: 1.0.0

Overview

This skill openly automates bulk five-star JD reviews from a logged-in account, but it can publish public content and install tooling without strong per-run user controls.

Review carefully before installing. Use only if you intentionally want an agent to operate your logged-in JD account, install or use browser automation tooling, and submit bulk five-star reviews publicly. Consider provisioning browser-use yourself, checking every review before submission, and confirming that this behavior complies with JD's rules and your own authenticity expectations.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (6)

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

print("未检测到 browser-use，正在自动安装...")
    try:
        subprocess.run(
            [sys.executable, "-m", "pip", "install", "browser-use"],
            check=True, capture_output=True, text=True
        )

• Confidence: 93% confidence
• Finding: subprocess.run( [sys.executable, "-m", "pip", "install", "browser-use"], check=True, capture_output=True, text=True )

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

[sys.executable, "-m", "pip", "install", "browser-use"],
            check=True, capture_output=True, text=True
        )
        subprocess.run(
            ["browser-use", "install"],
            check=True, capture_output=True, text=True, timeout=120
        )

• Confidence: 91% confidence
• Finding: subprocess.run( ["browser-use", "install"], check=True, capture_output=True, text=True, timeout=120 )

Context-Inappropriate Capability

Medium

• Confidence: 96% confidence
• Finding: The skill's stated purpose is automating JD reviews, but it also silently installs and initializes external tooling. In a security review context this mismatch is risky because it introduces unnecessary code execution and network-fetch behavior that is not essential to the business function and can be abused through package or installer compromise.

Vague Triggers

High

• Confidence: 94% confidence
• Finding: The trigger condition is so broad that nearly any request related to JD product reviews will activate an automation that logs into a real account and performs bulk submissions. Overbroad triggering increases the chance of accidental activation for sensitive, irreversible actions on behalf of the user.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill describes mass posting from a logged-in e-commerce account but omits clear warnings about account access, irreversible submission, platform-policy risk, and the possibility of posting inaccurate reviews. In this context, the absence of strong user warnings makes misuse and accidental harm significantly more likely.

Natural-Language Policy Violations

Medium

• Confidence: 96% confidence
• Finding: The skill explicitly instructs the agent to post uniform five-star reviews and positive service impressions for all pending items regardless of actual user experience. This is deceptive content manipulation and can facilitate review fraud at scale, especially because it is paired with bulk account automation.

VirusTotal

66/66 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.