Chattts

Security checks across malware telemetry and agentic risk

Overview

This appears to be a purpose-aligned text-to-speech skill, but users should know their input text is sent to a configured backend service.

Install only if you are comfortable with the text you convert to speech being sent to the configured TTS backend. Check CHATTTS_API_URL or the default endpoint before use, avoid sending secrets or sensitive personal data, and prefer a backend you operate or explicitly trust.

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: 91% confidence
Finding: The script takes arbitrary user-supplied text and transmits it to a backend HTTP service without any explicit notice, consent flow, or indication to the user that their prompt leaves the local agent boundary. This creates a privacy and data-handling risk, especially because the default endpoint is a hard-coded private-network address, so users may assume processing is fully local when it may be handled by another service on the network.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal