ElevenLabs

Security checks across malware telemetry and agentic risk

Overview

The only identified issue is broad ElevenLabs activation wording, with no evidence of hidden, destructive, or data-exfiltrating behavior.

Installers should be aware that the skill may activate for broad or casual ElevenLabs mentions. Use explicit prompts for sensitive voice, audio, or account actions, and confirm before letting it spend credits, create content, or change ElevenLabs account resources.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The skill description says to use this skill for ANY ElevenLabs request, which is overly broad and can cause the agent to invoke the skill for vague or incidental mentions of ElevenLabs rather than for clearly intended connector operations. In an agent setting, this increases the chance of unintended tool execution and may bypass more appropriate user clarification or narrower workflows.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal