ClawHub
Back to skill

Security audit

Galleon LI.FI Cross Chain

Security checks for vulnerabilities and agentic risk

Overview

This skill gives bounded LI.FI bridge quoting and settlement guidance without signing transactions or adding hidden persistence.

Before installing, understand that this skill is for LI.FI cross-chain quote and settlement analysis. It should not sign or send transactions, but users should still verify chain IDs, token addresses, recipient, slippage, approvals, and current LI.FI documentation before acting on any unsigned transaction terms.

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
Category
Not specified by scanner
Confidence
89% confidence
Finding

The default prompt broadly instructs the system to use the skill for a protocol task without defining clear boundaries, prerequisites, or disambiguation conditions. Because implicit invocation is enabled, this can cause the skill to be selected in loosely related contexts, increasing the chance of overbroad tool use, incorrect cross-chain guidance, or unnecessary exposure of workflow context in a sensitive financial domain.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.