Feishu Voice Bubble

Security checks across malware telemetry and agentic risk

Overview

This skill appears to perform its stated voice-message workflow, but users should know their text is sent to external TTS and messaging services.

Before installing, assume any text you ask it to voice may leave your machine for Microsoft Edge TTS processing, and the resulting audio may be uploaded to Feishu/Lark. Do not use it for secrets, credentials, private personal data, or regulated business content unless that data sharing is acceptable.

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 (2)

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill explicitly relies on Microsoft-hosted Edge TTS and then describes sending resulting audio to Feishu, but it does not prominently warn that user-provided text/audio content will leave the local environment and be transmitted to third parties. In contexts where users may dictate sensitive business, personal, or regulated information, this omission can lead to unintended data disclosure.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The script sends arbitrary input text to Microsoft's Edge TTS backend via a networked library, but there is no explicit user-facing warning or consent check at the point of transmission. Because this skill is specifically intended for chat message content, users may paste sensitive or regulated data that is then disclosed to a third-party service unexpectedly.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal