ClawHub
Back to skill

Security audit

OWS - Open Wallet Standard

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent and not deceptive, but it enables wallet signing and paid API payments without clear confirmation or financial-risk instructions.

Install only if you are comfortable with an agent being guided to use a local wallet CLI. Before any signing or payment action, require the agent to show the wallet name, chain, destination or URL, amount, fees, and exact transaction/message, and approve it explicitly yourself. Do not provide raw private keys.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly advertises transaction signing and x402 payment actions but does not include a clear warning that these operations can move funds, create irreversible blockchain transactions, or incur real financial loss. In an AI-agent context, exposing signing and payment commands without prominent confirmation and risk guidance increases the chance of accidental or unauthorized-value transfers triggered by ambiguous user prompts.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.