ClawHub
Back to skill

Security audit

Voice Clone TTS

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent voice-cloning/TTS helper, but voice cloning is sensitive and the instructions do not require clear speaker consent before uploading samples to third-party providers.

Review this skill carefully before installing. Use it only for voices you own or have explicit permission to clone, avoid sensitive or regulated text unless the selected provider is approved for that data, and check each provider's retention, privacy, and commercial-use terms.

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
  • 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 (8)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill enables voice cloning from uploaded samples without an explicit consent and authorization warning, creating a meaningful risk of impersonation, privacy violation, and misuse of another person's voice. In this context, voice cloning is inherently sensitive, so omitting a clear requirement to verify ownership/consent makes the skill materially more dangerous than ordinary TTS functionality.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill routes uploaded voice samples and synthesis text to external third-party TTS/voice-cloning providers, but it does not clearly disclose this data transfer to users at the point of use. Because voice recordings are biometric-like personal data and text may contain sensitive content, lack of explicit notice can cause inadvertent privacy exposure and noncompliant handling of user data.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The document promotes voice-cloning features as benefits but does not warn about consent, impersonation, biometric privacy, or legal/compliance risks. In a voice-cloning skill, this omission is security-relevant because users may be encouraged to clone or synthesize another person's voice without authorization, enabling fraud, deception, or privacy violations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The API examples show user text being sent to third-party TTS providers without disclosing that prompts/content leave the local environment. This can mislead operators into transmitting sensitive, regulated, or confidential text externally, especially in workflows involving narration, customer data, or internal documents.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
83% confidence
Finding

This example performs an outbound API request to MiniMax and transmits text plus credentials to an external service. External transmission itself is expected for cloud TTS, but in the absence of accompanying disclosure and data-handling warnings, it creates a real risk of unintended sharing of sensitive content.

Content

Scanner excerpt · references/backend-setup.md (reported line 33)May include surrounding context.

bash
# 语音合成
curl -X POST "https://api.minimax.chat/v1/text_to_speech" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
83% confidence
Finding

This example performs an outbound API request to MiniMax and transmits text plus credentials to an external service. External transmission itself is expected for cloud TTS, but in the absence of accompanying disclosure and data-handling warnings, it creates a real risk of unintended sharing of sensitive content.

Content

Scanner excerpt · references/backend-setup.md (reported line 33)May include surrounding context.

bash
# 语音合成
curl -X POST "https://api.minimax.chat/v1/text_to_speech" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
83% confidence
Finding

This curl example sends input text and an API key to OpenAI's external TTS endpoint. In a setup guide, that is normal functionality, but without notice about external processing and potential exposure of sensitive content, the documentation can enable unsafe deployment practices.

Content

Scanner excerpt · references/backend-setup.md (reported line 191)May include surrounding context.

API 示例

bash
curl https://api.openai.com/v1/audio/speech \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
83% confidence
Finding

This curl example sends input text and an API key to OpenAI's external TTS endpoint. In a setup guide, that is normal functionality, but without notice about external processing and potential exposure of sensitive content, the documentation can enable unsafe deployment practices.

Content

Scanner excerpt · references/backend-setup.md (reported line 191)May include surrounding context.

API 示例

bash
curl https://api.openai.com/v1/audio/speech \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

Static analysis

No suspicious patterns detected.