ClawHub
Back to skill

Security audit

Agent Stress Index

Security checks across malware telemetry and agentic risk

Overview

This paid crypto-signal skill is mostly transparent, but it needs Review because it asks an agent to use a wallet private key for automatic paid calls without built-in spending controls.

Review before installing. Use only a dedicated low-balance wallet, assume each call can spend USDC on Base, confirm costs before first use, and avoid exposing a primary wallet private key to an agent environment.

SkillSpector

By NVIDIA
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 skill instructs the agent to use an on-chain private key from EVM_PRIVATE_KEY to make an x402-authenticated paid request, but it does not clearly warn that this can spend wallet funds and expose transaction/payment metadata. In an agent setting, describing automatic payment handling without explicit consent boundaries, spending limits, or privacy warnings increases the risk of unintended financial charges and unsafe secret use.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal