ClawHub
Back to skill

Security audit

ButterSwap

Security checks across malware telemetry and agentic risk

Overview

This is a transparent ButterSwap helper for quotes and transaction payloads, but users must review wallet and transaction details before signing anything.

Install only if you are comfortable sending swap intent and wallet-address details to Butter Router. Use it for quotes and transaction construction, then independently verify token addresses, chain IDs, receiver/refund addresses, route, fees, slippage, approval amount, contract target, calldata summary, and native value in your wallet before signing.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The README explicitly promotes generating swap and approve transaction payloads, which can directly lead to irreversible token movements or dangerous token approvals if integrated without user safeguards. In a cross-chain swap skill, missing warnings about approval scope, destination validation, slippage, and irreversibility materially increases the chance that downstream agents or developers will build unsafe transaction flows.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The quick-start example calls the swap API with wallet-related fields such as `from` and `receiver` but provides no warning that these values may expose wallet metadata to a third-party service or produce executable transaction data. In the context of a skill designed to help agents build cross-chain swap transactions, omission of privacy and transaction-safety guidance makes accidental misuse more likely.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger list contains broad phrases such as "swap tokens" and "bridge tokens" that can cause the skill to activate in contexts where the user did not specifically intend to use this external cross-chain routing service. In a financial and blockchain context, unintended invocation is risky because it may lead the agent to solicit wallet addresses, query third-party APIs, or present transaction-building flows for the wrong task.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs the agent to collect and send wallet addresses, routing parameters, and transaction-related data to an external API, but it does not clearly warn users that this information will leave the local environment. In a crypto workflow, address disclosure and transaction intent metadata can expose sensitive financial behavior, create privacy risks, and reduce informed consent before interacting with a third-party service.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.