ClawHub
Back to skill

Security audit

Unified API for powerful image and video generation

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a straightforward AIsa media-generation helper that sends prompts to AIsa and saves generated output when the user asks it to.

Install only if you trust AIsa and the publisher. Use a revocable AISA_API_KEY, do not submit secrets or private media unless allowed, and choose output paths carefully because downloads and generated images write to the path you provide.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

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
91% confidence
Finding
The downloader fetches an arbitrary URL returned by the task response and writes the response body directly to disk without validating scheme, host, content type, or size. If an attacker can influence the video URL or task response, this creates an SSRF-style outbound fetch and untrusted file write that could pull internal resources or store unexpected/malicious content locally.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.