Venice API Kit

• Outcome: Pass
• Latest audit: May 28, 2026, 3:48 AM
• Version:
  2.0.2

Overview

This is a disclosed Venice AI API toolkit whose network use, file inputs, generated outputs, and admin API-key operations match its stated purpose.

Install only if you intend to send selected prompts, media, audio, text files, and admin requests to Venice AI. Use an inference key for normal generation tasks, reserve admin keys for billing and API-key management, and review any local file path before running upload-style commands.

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 (3)

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The examples encourage sending prompts, images, audio, and files to an external API, but they do not place a clear warning alongside those commands that user-supplied content leaves the local environment. Although the document later mentions privacy and trust generally, that is not sufficient for informed consent at the point of use, especially for sensitive media, transcriptions, or admin operations.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: When the --file option is used, the script reads the entire local file and sends its contents to a remote embeddings API, but it does not provide an explicit consent prompt or strong warning that local data will leave the machine. In a toolkit context, users may embed sensitive files by mistake, creating a real data disclosure risk even though the transmission is part of the intended functionality.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The script uploads the full contents of a user-supplied audio file to a remote Venice API endpoint for transcription, but it does not provide an explicit consent prompt or strong warning at the point of transmission. Because audio may contain sensitive personal, business, or regulated data, silent remote transfer can create privacy and compliance risk even if the behavior is the tool's intended function.

VirusTotal

64/64 vendors flagged this skill as clean.