ClawHub
Back to skill

Security audit

Base toolbox

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Base blockchain analysis helper that requires fresh user approval before paid calls or transaction-related actions, with only a minor broad-trigger caveat.

Before installing, understand that using paid POST endpoints may disclose wallet and transaction details to the listed remote service and PayAI. Only approve exact payment offers you recognize, and keep the skill's own safeguards: never approve unlimited allowances and do not sign or submit transactions based only on remote calldata.

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
Confidence
89% confidence
Finding
The trigger list includes several broad terms such as "allowance," "revoke," "honeypot," and token symbols like "WETH USDC" that could match ordinary user conversations and activate the skill when the user did not explicitly request this remote HTTP/payment-enabled tool. Because the skill can prompt for paid API calls and handle transaction-related data, unintended activation increases the chance of confusing consent flows, unnecessary data disclosure to the remote operator, or accidental payment prompts.

Static analysis

No suspicious patterns detected.