企业法律避坑专家

• Outcome: Review
• Latest audit: May 31, 2026 at 5:36 PM UTC
• Version:
  1.0.0

Overview

The skill appears to be a coherent legal-risk screening and paid consultation funnel, but it asks for sensitive business/legal details without a privacy notice and can activate on broad terms.

Review carefully before installing. Use it only when you intentionally want a Chinese enterprise legal-risk screening, avoid sharing confidential or privileged details unless you trust the publisher and data handling, and verify the lawyer identity and payment destination before sending money or payment screenshots.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The trigger phrases are generic business/legal terms and the README does not define clear activation boundaries, which increases the chance the skill is invoked in unrelated conversations about compliance or risk. Unintended invocation can steer users into this skill’s commercial funnel and expose them to legal-sounding guidance when they did not explicitly request this specific tool.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger phrases include broad terms such as “避坑” and “风险检测,” which can appear in many unrelated conversations and cause the skill to activate unexpectedly. In this skill’s context, unintended activation is more concerning because the workflow immediately steers users into collecting business details and a paid legal-assessment funnel, increasing the chance of inappropriate data collection or commercial prompting.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The workflow section repeats activation conditions that are loosely scoped and do not require confirmation that the user actually wants a legal-risk assessment for an enterprise. Because the skill presents itself as an expert legal checker and begins intake immediately, ambiguous activation can misroute users, solicit sensitive company information, and push legal/paid guidance in contexts where it was not requested.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The intake template requests identifiable business information including company name, industry, size, and business description without any privacy notice, retention statement, minimization guidance, or warning not to share confidential data. In a legal-risk context, these details can be commercially sensitive and may reveal regulated, tax, employment, or dispute-related exposure, making silent collection materially risky.

VirusTotal

VirusTotal findings are pending for this skill version.