ClawHub

Openclaw-X-article-cover-generator

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed cover-image generator that uses an external image API and saves the generated image to a user-chosen file, with privacy and validation cautions.

Install only if you are comfortable sending the title, subtitle, and any reference image to the BLT image API. Avoid sensitive reference images, use a dedicated API key where possible, and choose the output path carefully because the script writes the returned image there.

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 (3)

Tainted flow: 'data' from requests.get (line 81, network input) → pathlib.Path.write_bytes (file write)

Medium
Category
Data Flow
Content
def save_from_url(url: str, out: Path):
    data = requests.get(url, timeout=120).content
    out.parent.mkdir(parents=True, exist_ok=True)
    out.write_bytes(data)


def main():
Confidence
93% confidence
Finding
out.write_bytes(data)

Tainted flow: 'url' from os.environ.get (line 140, credential/environment) → requests.get (network output)

Critical
Category
Data Flow
Content
def save_from_url(url: str, out: Path):
    data = requests.get(url, timeout=120).content
    out.parent.mkdir(parents=True, exist_ok=True)
    out.write_bytes(data)
Confidence
78% confidence
Finding
data = requests.get(url, timeout=120).content

Missing User Warnings

Medium
Confidence
88% confidence
Finding
A local reference image may be base64-encoded and transmitted to a third-party image-generation API, but the script does not present an explicit warning or confirmation at the point of use. In a skill context, users may unknowingly upload sensitive local images or proprietary assets to an external service.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal