ClawHub
Back to skill

Security audit

Venice AI Media

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent Venice AI media tool, but users should avoid sending sensitive media or prompts to the third-party API.

Install this only if you intend to use Venice AI. Use a dedicated revocable API key, prefer environment variables or protect ~/.clawdbot/clawdbot.json carefully, check video pricing before long jobs, and do not submit sensitive photos, documents, private URLs, audio, or confidential prompt text unless Venice AI's policies are acceptable to you.

SkillSpector

By NVIDIA
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 (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill documentation indicates capabilities to read/write files, access environment variables, and make network requests, yet it does not declare permissions. This creates a transparency and governance gap: users and reviewers may not understand the true access the skill requires, increasing the risk of over-privileged execution and unsafe trust decisions.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The instructions recommend storing the Venice API key in a persistent local config file without any guidance on file permissions, secret handling, or avoiding accidental disclosure. This can lead to credential exposure through backups, shared home directories, screenshots, logs, or source-control mistakes, especially because the key grants billable third-party API access.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
When a user supplies an HTTP(S) image URL, the script automatically downloads that remote content locally and then forwards the image data to the Venice API. This creates a real privacy risk because third-party image content may contain sensitive information, and the transfer occurs without an explicit disclosure, confirmation step, or domain allowlisting; additionally, fetching arbitrary URLs can unintentionally access internal or private resources if the runtime has network reachability.

External Transmission

Medium
Category
Data Exfiltration
Content
audio_url: str | None,
) -> dict:
    """Queue a video generation request."""
    url = "https://api.venice.ai/api/v1/video/queue"

    payload: dict = {
        "model": model,
Confidence
89% confidence
Finding
https://api.venice.ai/

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.