ClawHub
Back to skill

Security audit

Swap Tokens

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed token-swap helper that can trigger on broad trading language, but its behavior is coherent with its purpose and requires human confirmation before value-moving swaps.

Install only if you want an agent to help perform on-chain token swaps through fdx. Treat every proposed swap as a financial transaction: verify token addresses, chain, amount, slippage, and destination asset before approving execution.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The description includes very broad trigger phrases such as "buy," "sell," "convert," and especially "get some ETH," which can match ambiguous user intents and cause the swap skill to be invoked when the user did not clearly request an on-chain token trade. Because this skill can lead to financial transactions, unintended invocation is more dangerous here than in a read-only skill: it increases the chance of prompting or initiating value-moving actions in the wrong context.

Static analysis

No suspicious patterns detected.