Security audit

Text to Speech and Voice Cloning by Verbatik AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly disclosed Verbatik text-to-speech integration, but it enables voice cloning and voice deletion without consent, confirmation, or misuse guardrails.

Install only if you are comfortable giving the assistant access to a Verbatik API key and sending text plus voice-sample URLs to Verbatik. Require explicit consent from the voice owner before cloning, confirm costs before paid operations, and require a separate confirmation before deleting any cloned voice.

A.I.G

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

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Tool Parameter Abuse

High

Category: Tool Misuse
Confidence: 88% confidence
Finding: The skill exposes a destructive deletion operation for cloned voices without any mention of confirmation, authorization checks, scoping, or user-intent verification. In an autonomous agent setting, this increases the risk of accidental or prompt-induced deletion of user assets, especially if a malicious prompt tricks the agent into invoking the endpoint.
Content: Scanner excerpt · SKILL.md (reported line 175)May include surrounding context.
Delete a voice:

text
DELETE /api/v1/my-voices/<voice_id>

6. Preview a Pre-trained Voice

External Transmission

Medium

Category: Data Exfiltration
Confidence: 50% confidence
Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Content: Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.
Verbatik also exposes an MCP server for direct AI assistant integration. Endpoint:

text
https://api.verbatik.com/api/mcp/mcp

Supports OAuth 2.1 (one-click connect in Claude Desktop) and API key auth via mcp-remote bridge.

Missing User Warnings