ClawHub
Back to skill

Security audit

Indextts Voice

Security checks across malware telemetry and agentic risk

Overview

Review recommended because the skill appears to support voice cloning and third-party audio upload without clear permission and consent disclosures.

Install only if you trust the publisher and provider, understand where audio is uploaded, and will use reference voices only with explicit authorization. Confirm the required secret, contacted API domain, provider retention/deletion terms, and consent safeguards before using cloning workflows.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill documentation clearly relies on sensitive environment variables (`INDEX_API_SIGN`) and outbound network access to a third-party API, yet it declares no permissions. That mismatch can mislead users and hosting platforms about the skill’s actual capabilities, reducing informed consent and weakening policy enforcement or sandbox review.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This skill facilitates voice cloning and reference-audio upload, which involve biometric voice data and can enable impersonation if used without consent. The absence of prominent warnings and usage constraints around consent, privacy, retention, and lawful use increases the risk of misuse, especially because cloned voice workflows are inherently sensitive.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal