Security audit

Swap and bridge across 35+ chains with LI.FI

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed LI.FI helper for cross-chain quotes and transaction data, with expected external API calls and no hidden code or persistence.

Before installing, treat every returned transactionRequest as a real blockchain transaction that can move funds. Verify chain, token, address, amount, slippage, fees, route, contract calls, and ERC20 allowance in the wallet before signing, and expect LI.FI to receive the wallet and transaction details needed to quote or track transfers.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The README promotes cross-chain swaps, bridges, and DeFi zaps—operations that can trigger irreversible on-chain transactions and token approvals—but does not prominently warn users about loss-of-funds risk, slippage, bridge failure modes, or the need for explicit confirmation before signing. In an agent-execution context, this omission is especially dangerous because users may treat the commands as routine automation and underestimate that the returned transaction requests can move assets permanently across chains.
Content: No source excerpt is available for this finding.

External Transmission