Back to skill

Security audit

Nodo: Logged-In Cloud Browser

Security checks for vulnerabilities and agentic risk

Overview

The skill clearly discloses a cloud browser that retains logins, and its instructions fit that purpose.

Installing connects your agent to a service that retains signed-in website sessions. Review current setup instructions and access permissions, use only authorized accounts, and explicitly approve recurring work. Both scanners reported no findings; remote setup contents and the provider's credential-storage claims remain unverified.

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