ClawHub
Back to skill

Security audit

Trust Escrow

Security checks for vulnerabilities and agentic risk

Overview

This documentation-only skill matches its escrow purpose, but users should be careful because its examples can sign blockchain transactions.

Before using this skill, verify the network, contract address, receiver address, amount, token decimals, deadline, and allowance size. Use test funds, approve only the minimum needed, and require explicit human review before any wallet signs approve, create, release, cancel, dispute, or batch transactions.

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 (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation includes executable examples for approving USDC and creating/releasing escrow transactions, but it does not clearly warn that these actions move funds, may grant token spending allowances, and are generally irreversible once confirmed on-chain. In an agent-executed context, this omission increases the risk that users or downstream agents will run the example flow without understanding financial consequences or verifying recipient, contract, and network details.

Static analysis

No suspicious patterns detected.