ClawHub
Back to skill

Security audit

ClawPay-Hedera

Security checks for vulnerabilities and agentic risk

Overview

This payment skill appears purpose-aligned, but it handles a blockchain private key in a contradictory and potentially exposing way.

Review before installing. Use only a dedicated Hedera testnet wallet or a wallet with minimal funds, avoid examples that pass private keys via command-line flags, and prefer SDK modes that read credentials directly from environment variables or a secret manager. Treat any mainnet use as real spending authority.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
This is a mismatch because the description advertises a full Hedera payment and agent-discovery/reputation workflow, but the provided code does not implement those capabilities. It only performs local environment validation and prints instructions for using the ClawPay CLI. While the setup script is loosely related to the payment theme, the actual behavior falls far short of the declared purpose and omits several major claimed features.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger example "The user mentions ClawPay, paid tools, agent registry, or Hedera payments" is broad enough that ordinary discussion about agents or payments could match, without clearly distinguishing when the skill should or should not activate. The file does not provide exclusion conditions or negative examples to narrow the trigger scope.

Static analysis

No suspicious patterns detected.