ClawHub
Back to skill

Security audit

Edge Tts Unlimited

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward text-to-speech helper, with ordinary dependency and privacy cautions but no evidence of malicious behavior.

Install only if you are comfortable with runtime Python package installation and external TTS processing. Avoid sending secrets, private documents, regulated data, or proprietary text through this skill unless your policy allows that content to leave the machine.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The script performs an implicit `pip3 install -q edge-tts` at runtime if `uv` and `edge-tts` are not already present. This expands the skill's behavior from local text-to-speech generation to network-based package installation and execution of newly fetched code, which creates supply-chain risk, non-deterministic behavior, and unexpected environment modification. In the context of an agent skill, this is more dangerous because simply invoking TTS can trigger dependency installation without explicit user consent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.