ClawHub
Back to skill

Security audit

Elevenlabs Transcribe

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: transcribes user-selected audio through ElevenLabs, with expected privacy and dependency caveats but no hidden or destructive behavior found.

Install only if you are comfortable sending the audio or stream URLs you choose to transcribe to ElevenLabs under your API key. Use microphone mode intentionally, avoid confidential or non-consented recordings, protect ELEVENLABS_API_KEY, and verify the publisher if the 'Official ElevenLabs skill' claim matters to your trust decision.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (6)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documentation describes transcribing local files, microphone input, and remote streams with ElevenLabs but does not clearly warn users that the audio content is sent to a third-party cloud service for processing. This can cause unintentional disclosure of sensitive conversations, recordings, or stream content, especially in agent or automation contexts where users may assume processing is local.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The microphone mode captures live audio and streams it to ElevenLabs for transcription, but the script does not provide an explicit warning or consent prompt at the point of capture that audio leaves the local system. In a CLI/tooling context this can cause unintended disclosure of sensitive spoken content, especially if embedded in larger workflows or invoked by other agents on behalf of a user.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
Batch transcription reads a local file and uploads its contents to a third-party API, but the code does not explicitly disclose this remote upload at execution time. Users may assume local processing from the CLI wording alone, which can lead to accidental exposure of confidential recordings.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The URL realtime mode forwards a user-supplied stream URL to an external service, which may cause the remote service to fetch or process data from that source without a clear disclosure to the operator. This creates privacy and data-handling risk because both the URL and stream contents may be exposed to a third party.

Unpinned Dependencies

Low
Category
Supply Chain
Content
# Platform-specific packages - pinned versions only (hashes vary by platform)
sounddevice==0.5.1
numpy>=1.24.0
Confidence
95% confidence
Finding
numpy>=1.24.0

Known Vulnerable Dependency: python-dotenv==1.0.1 — 1 advisory(ies): CVE-2026-28684 (python-dotenv: Symlink following in set_key allows arbitrary file overwrite via )

Low
Category
Supply Chain
Confidence
84% confidence
Finding
python-dotenv==1.0.1

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.