ClawHub

AI Media Generation

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward AIsa media-generation helper that uses a user-provided API key, sends media prompts to AIsa, and saves generated files locally when explicitly run.

Install only if you trust the publisher and AIsa service. Do not submit secrets, private prompts, or sensitive image URLs unless approved for that provider, and choose output paths carefully because generated files may overwrite existing files. Treat automatic video download as less hardened because it trusts the provider-returned download URL.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Tainted flow: 'req' from os.environ.get (line 65, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Content
os.makedirs(os.path.dirname(out_path) or ".", exist_ok=True)
    req = urllib.request.Request(url, headers={"User-Agent": "OpenClaw-Media-Gen/1.0"})
    try:
        with urllib.request.urlopen(req, timeout=timeout_s) as resp, open(out_path, "wb") as f:
            total = 0
            while True:
                chunk = resp.read(1024 * 1024)  # 1MB
Confidence
85% confidence
Finding
with urllib.request.urlopen(req, timeout=timeout_s) as resp, open(out_path, "wb") as f:

Missing User Warnings

Low
Confidence
91% confidence
Finding
The README instructs users to provide an API key and send prompts, image URLs, and media-generation requests to the external AIsa service, but it does not clearly disclose that user inputs and referenced media are transmitted to a third party. This can lead users to unintentionally expose sensitive prompts, proprietary media, or personal data to an external provider, especially in enterprise or privacy-sensitive environments.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal