ClawHub
Back to skill

Security audit

ElevenLabs Speech-to-Text

Security checks for vulnerabilities and agentic risk

Overview

This transcription skill appears purpose-built for ElevenLabs, but users should review it because it uploads audio to a third party and handles the API key in a way that may expose it locally.

Install only if you are comfortable sending selected audio files to ElevenLabs for processing. Avoid using it for confidential, regulated, or third-party recordings unless you have approval, and consider hardening the script so the API key is not passed through process command-line arguments.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/transcribe.sh:66
Finding

ElevenLabs API Key Exposed Through Process Command-Line Arguments

Content
View full analysis
Remediation
View remediation
"$HEADER_FILE" CURL_ARGS=( -s -X POST "https://api.elevenlabs.io/v1/speech-to-text" -H "@$HEADER_FILE" -F "file=@$FILE" -F "model_id=scribe_v2" -F "diarize=$DIARIZE" -F "tag_audio_events=$TAG_EVENTS" ) ``` The temporary file must remain readable only by the invoking user and must always be deleted after the request. ]]>

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The README describes local transcription commands and features but does not clearly warn users that supplied audio is uploaded to ElevenLabs, a third-party service, for processing. This can cause users to unknowingly send sensitive voice recordings, meetings, or regulated data off-device, creating privacy, confidentiality, and compliance risks.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill exposes shell-based functionality but does not declare an explicit tool scope such as permissions or allowed-tools. That creates ambiguity about what execution capabilities the skill requires and can lead to overbroad or unintended shell access when the skill is invoked.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill sends user-provided audio to ElevenLabs for transcription, but the description does not clearly warn users that their files leave the local environment and are uploaded to a third-party service. This can expose sensitive voice content, background conversations, or regulated data without informed user consent, especially in enterprise or personal contexts.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The script uploads the supplied audio file to ElevenLabs' external speech-to-text service, but its help text and normal output do not clearly warn users that local audio contents will leave the system and be processed by a third party. This creates a meaningful privacy and data-handling risk, especially if users transcribe sensitive recordings without realizing they are being transmitted off-host.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

This script intentionally sends user-provided audio to an external network endpoint and includes an API credential in the request header. In the context of a transcription skill this behavior is expected, but it is still security-relevant because it transfers potentially sensitive content to a third party and therefore requires clear disclosure and trust assumptions.

Content

Scanner excerpt · scripts/transcribe.sh (reported line 71)May include surrounding context.

sh
CURL_ARGS=(
    -s
    -X POST
    "https://api.elevenlabs.io/v1/speech-to-text"
    -H "xi-api-key: $API_KEY"
    -F "file=@$FILE"
    -F "model_id=scribe_v2"

Static analysis

No suspicious patterns detected.