Security audit

中国商标查询 Skill

Security checks across malware telemetry and agentic risk

Overview

The skill is a disclosed Chinese trademark search connector, with a billing-language inconsistency users should verify before relying on trial credits.

Before installing, verify the current trial-credit terms in the platform UI because the English and Chinese pricing text disagree. Treat the platform token like a password, use HTTPS, and expect trademark queries and usage history to be processed by the hosted service in mainland China.

SkillSpector

By NVIDIA

Vulnerability Patterns

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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 (2)

Intent-Code Divergence

Medium

Confidence: 97% confidence
Finding: The English and Chinese versions define materially different trial-point terms: English says 10 trial points expiring in 30 days, while Chinese says 100 trial points expiring in 90 days. In a billing document, contradictory language can mislead users about cost, entitlement, and expiry, creating dispute risk and enabling selective enforcement based on user language.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: Inconsistent bilingual policy content can cause users to accept different effective terms depending on which language they read, without explicit disclosure or consent. In this pricing context, that can affect trial credits and expiry expectations, leading to unfair treatment, complaints, chargebacks, or regulatory scrutiny for deceptive or unclear billing practices.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec, suspicious.env_credential_access, suspicious.exposed_secret_literal

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/cli.test.mjs:54

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: scripts/cli.mjs:323

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: API_CONTRACT_EN.md:68

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: API_CONTRACT.md:68