ClawHub
Back to skill

Security audit

Openai Tts.Bak 2026 01 28T18:01:23+10:30

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward OpenAI text-to-speech skill that sends the text you provide to OpenAI using your API key, with no hidden or unrelated behavior found.

Install only if you are comfortable sending the text you pass to the script to OpenAI for speech generation and paying for use on the configured API key. Avoid sending secrets, regulated data, or private content unless your policy allows it, protect any stored API key, and make sure jq is installed.

SkillSpector

By NVIDIA
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
Confidence
97% confidence
Finding
The skill accepts arbitrary text and sends it to OpenAI's external `/v1/audio/speech` API, but the description and quick-start guidance do not clearly warn users that their input leaves the local environment. This can lead to unintentional disclosure of sensitive prompts, secrets, personal data, or proprietary text when users assume the conversion happens locally.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.