Ethereum L2 Analytics 以太坊L2分析

• Outcome: Review
• Latest audit: May 28, 2026 · 7:16 AM UTC
• Version: 1.0.0

Overview

This Ethereum L2 analytics skill mostly matches its stated purpose, but it has an under-disclosed paid SkillPay verification flow that can send wallet data to an external service and uses an embedded API key.

Review before installing. Use it only if you are comfortable with a paid-use flow, an embedded SkillPay credential, and possible sharing of a wallet address with SkillPay. Do not rely on its bridge or token recommendations for real fund movement or investment decisions without independently verifying official URLs, contract addresses, fees, supported networks, and your own risk tolerance.

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
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (6)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 89% confidence
• Finding: The skill declares no permissions while static analysis detected environment, file-write, and network-capable behavior. Hidden capabilities are dangerous because they expand the attack surface and can enable data exfiltration, unauthorized file modification, or unexpected outbound requests without informed user or platform consent.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 97% confidence
• Finding: This is a serious description-behavior mismatch: a blockchain analytics skill reportedly performs third-party payment verification, uses a hardcoded API key, emits payment links, and allows payment checks to be bypassed via environment variables. That combination strongly suggests concealed monetization and secret handling behavior unrelated to the stated purpose, creating risks of credential leakage, deceptive billing flows, and unauthorized external communication.

Description-Behavior Mismatch

High

• Confidence: 94% confidence
• Finding: The file adds payment-gating behavior to a skill described as Ethereum L2 analytics, creating a capability mismatch that can conceal monetization or access-control logic not implied by the declared purpose. This is dangerous because users and reviewers may invoke the skill expecting analytics-only behavior while the code enforces payment checks and communicates with an external service using a bundled secret.

Context-Inappropriate Capability

Medium

• Confidence: 91% confidence
• Finding: The code performs external payment verification against a third-party API even though the stated skill purpose is analytics. Unjustified external capability increases attack surface, enables hidden data sharing, and can be abused to gate or track users in ways not evident from the skill description.

Description-Behavior Mismatch

Medium

• Confidence: 92% confidence
• Finding: The code explicitly generates investment recommendations such as '强烈推荐' and '可考虑配置', which crosses from analytics into financial advice. In an agent skill, this can cause users or downstream automations to treat heuristic outputs as actionable investment guidance without suitability checks, disclosures, risk controls, or regulatory safeguards.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The skill transmits the user's wallet address and a precise timestamp to an external API without any visible consent flow or clear disclosure in this module. Wallet addresses are persistent identifiers, so this enables user tracking and linkage of activity across sessions and services.

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.