Back to skill

Security audit

Ethereum JSON-RPC Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill gives an agent a clearly scoped way to perform read-only Ethereum JSON-RPC queries and user-controlled subscription streams.

Install only if you want agents to query public Ethereum execution RPC data through UXC. Review subscription use because it can create long-running jobs and local event log files; keep the documented read-only guardrails unless you separately approve broader Ethereum RPC authority.

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
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.