Back to skill

Security audit

send-ai-voice-message-via-sms

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple disclosed SMS voice-message workflow, with ordinary privacy and consent considerations for sending messages to phone numbers.

Before using it, confirm the recipient phone number, message content, and authorization to contact the recipient, especially for appointment or customer details sent outside your organization.

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
  • 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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly supports generating personalized content and sending it to a phone number via SMS, but it does not clearly warn users about external delivery, recipient verification, consent, or privacy risks. In a communication skill, this omission increases the chance of misdirected messages, unauthorized outreach, or disclosure of sensitive appointment details to the wrong recipient.

Content

No source excerpt is available for this finding.