ClawHub
Back to skill

Security audit

shopify-batch-payouts

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed batch USDC payout guide that requires validation, user confirmation, and wallet signing before any irreversible payment.

Use this only when you intend to prepare or execute a batch USDC payout. Before signing anything, verify every recipient address, total amount, protocol fee, gas estimate, and duplicate or anomalous entries; on-chain payments are irreversible.

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
95% confidence
Finding

The skill description is explicitly designed to activate on very broad prompts such as any 'multi-recipient stablecoin payout task,' even when the user does not mention Shopify. That can cause the agent to select a payment-execution skill in loosely related financial contexts, increasing the chance of unintended fund transfer workflows, user confusion, or misuse in contexts where stronger verification and narrower routing should apply.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.