Back to skill

Security audit

Nodo: Real Phone for Your Agent

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a coherent cloud-phone workflow, with disclosed reliance on Nodo for sensitive accounts and scheduled tasks.

Treat Nodo as a trusted custodian of any messages, verification codes and account sessions placed on its devices. Before using sensitive accounts, check its privacy and deletion controls and specify which actions require approval. Confirm schedules, ongoing costs and how to stop workflows and revoke sessions. The complete packaged skill was inspected, but the external setup guide and live service controls 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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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
Findings (1)

The workflow directs use of a third-party cloud phone for potentially sensitive tasks without a privacy warning.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The skill explicitly promotes handling SMS verification codes, 2FA, and potentially banking applications on a third-party cloud phone without explaining that sensitive messages, credentials, and app sessions cross into provider-managed infrastructure. Browser sign-in approval does not establish informed consent for that exposure; a provider compromise or inappropriate access could expose authentication codes and enable account compromise. The authorized-use restriction is helpful, but it does not address this privacy and trust-boundary risk, and the file provides no evidence of an actual leak or malicious intent.

Content

No source excerpt is available for this finding.