Openai Whisper Api Hardened

• Outcome: Review
• Latest audit: May 29, 2026 at 9:35 PM UTC
• Version:
  1.0.0

Overview

The skill mostly does what it says, but its wrapper has an input-handling flaw that could unintentionally send local file contents to OpenAI.

Install only if you are comfortable sending chosen audio files to OpenAI with your API key. Until the script is fixed to use literal form fields, avoid untrusted or file-derived --prompt, --model, and --language values, especially values that start with @ or <.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The script uploads the supplied audio file to OpenAI's external transcription API, but it does not provide an explicit user-facing warning or consent prompt at the point of transmission. This can lead to unintended disclosure of sensitive audio content, especially when the script is embedded in larger workflows where users may not realize data leaves the local environment.

VirusTotal

66/66 vendors flagged this skill as clean.