ClawHub
Back to skill

Security audit

bridging

Security checks for vulnerabilities and agentic risk

Overview

This Celo bridging skill is coherent but needs Review because its examples can initiate real mainnet asset transfers without prominent consent, testnet-first defaults, or privacy warnings.

Review this skill carefully before installing or using it. Treat the examples as production-sensitive: verify contract addresses from official sources, prefer testnets first, require explicit confirmation of chain, amount, recipient, token, and bridge provider, and do not sign wallet prompts unless you understand the fees, delays, approvals, and transfer risk.

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
  • 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 (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The example performs a real payable bridge transaction to a live mainnet contract without an explicit warning that it moves real assets, incurs irreversible gas costs, and is subject to cross-chain finality and delay semantics. In an agent-skill context, users may treat example code as safe boilerplate and trigger transfers without understanding that funds can be locked in transit, delayed, or mis-sent if chain or address assumptions are wrong.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The LI.FI example shows quote retrieval and route execution for a cross-chain transfer but does not clearly disclose that it may send wallet/address data to third-party infrastructure and then initiate real asset movement across chains. Because route execution can involve multiple steps, approvals, and bridge providers, users may underestimate privacy exposure and the financial consequences of signing the resulting transactions.

Static analysis

No suspicious patterns detected.