DesignKit Ecommerce AI Studio

Security checks across malware telemetry and agentic risk

Overview

This appears to be a coherent DesignKit image-processing skill, with the main precautions being that it uses your API key and uploads user-provided images for remote processing.

Install only if you are comfortable using your DesignKit/OpenClaw API key and sending selected product images to the remote service. Prefer the inspected ClawHub install path, keep request logging off unless debugging, avoid private or sensitive images, and verify any custom output directory or API-base override before use.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

#
ASI02: Tool Misuse and Exploitation
Low
What this means

After you provide the needed image and parameters, the agent may run the bundled scripts to submit the job and download results.

Why it was flagged

The agent is expected to run local shell/Python executors after collecting task inputs. This is purpose-aligned for the image workflow, but users should expect tool execution and network submission.

Skill content
Once enough information is available, briefly restate the action in Chinese and execute it directly.
Recommendation

Use the skill only for intended image-processing tasks, and review the requested action before providing local paths or task details.

#
ASI03: Identity and Privilege Abuse
Medium
What this means

The skill can act against the DesignKit/OpenClaw service using your configured API key, which may affect account usage or credits.

Why it was flagged

The code reads the DesignKit/OpenClaw API key from the environment and uses it as an authentication header.

Skill content
ak = os.environ.get("DESIGNKIT_OPENCLAW_AK", "").strip() ... "X-Openclaw-AK": ak
Recommendation

Set the API key only in a trusted environment, rotate it if exposed, and avoid enabling verbose request logging unless needed.

#
ASI07: Insecure Inter-Agent Communication
Medium
What this means

Images you provide may leave your device and be processed by DesignKit/OpenClaw.

Why it was flagged

The data flow intentionally sends user-provided local images to a remote provider for processing; this is clearly disclosed and purpose-aligned.

Skill content
Local images supplied by the user may be uploaded to the remote DesignKit / OpenClaw API.
Recommendation

Only provide images you are comfortable uploading to the service, and do not set DESIGNKIT_WEBAPI_BASE to an untrusted endpoint.

#
ASI04: Agentic Supply Chain Vulnerabilities
Info
What this means

Installing directly from a moving repository may expose you to source changes that differ from the reviewed package.

Why it was flagged

The README offers an optional direct GitHub installation command. It is user-directed rather than automatic, but it is less controlled than installing an inspected ClawHub package.

Skill content
npx -y skills add https://github.com/meitu/designkit-skills
Recommendation

Prefer `clawhub inspect` and ClawHub installation, or pin and inspect the repository version before direct installation.