ClawHub
Back to skill

Security audit

erc-8004-development

Security checks across malware telemetry and agentic risk

Overview

This is a documentation skill for building ERC-8004 agent integrations, with disclosed blockchain, wallet, IPFS, and search behaviors that fit its stated purpose.

Install only if you intend to work with ERC-8004 or Agent0. Use testnet or throwaway keys for development, verify chain IDs before signing, avoid putting valuable wallet keys in environment variables, and treat semantic search keywords, registration metadata, feedback, and IPFS/on-chain records as potentially public or externally processed.

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 documentation states that semantic search uses an external endpoint (`semantic-search.ag0.xyz`) but does not clearly warn that user-supplied keywords are transmitted to a third-party service. In a search/discovery skill for on-chain agents, queries may contain sensitive business intent, internal investigation terms, or proprietary prompts, so omission of a privacy warning can lead to unintended data disclosure and trust boundary violations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.