← Back to Skills Marketplace
Image Detection
by
raghulpasupathi
· GitHub ↗
· v1.0.0
837
Downloads
0
Stars
5
Active Installs
1
Versions
Install in OpenClaw
/install image-detection
Description
Analyzes images to detect AI generation, extract metadata, identify artifacts, and perform content moderation using local and cloud-based tools.
README (SKILL.md)
Image Detection Skills
Skills for analyzing and detecting AI-generated images.
Essential Skills
1. Image Analyzer
Skill ID: image-analyzer
Purpose: Local image analysis without external APIs
Features:
- EXIF metadata extraction
- AI artifact detection (weird hands, blurred backgrounds)
- Visual similarity comparison
- Reverse image search integration
Installation:
npm install @clawhub/image-analyzer
Configuration:
{
"skill": "image-analyzer",
"settings": {
"detectArtifacts": true,
"extractMetadata": true,
"localOnly": true,
"checkSignatures": ["DALL-E", "Midjourney", "Stable-Diffusion"]
}
}
Use Cases: Fast local detection, metadata verification, artifact identification
2. HuggingFace Image Detector
Skill ID: hf-image-detector
Purpose: ML-based AI image detection
Features:
- Pre-trained models (umm-maybe/AI-image-detector)
- High accuracy (90-95%)
- Supports SD, Midjourney, DALL-E
- Local inference (no API calls)
Installation:
npm install @clawhub/hf-image-detector
Use Cases: High-accuracy detection, privacy-focused analysis
3. Hive Moderation API
Skill ID: hive-api
Purpose: Cloud-based image analysis
Features:
- AI-generated detection
- NSFW filtering
- Object detection
- Fast inference (500ms)
Installation: API integration via REST
Use Cases: Quick detection, multi-purpose analysis, NSFW filtering
Installation
Via ClawHub
https://clawhub.ai/raghulpasupathi/image-detection
Via npm
npm install @raghulpasupathi/image-detection
Configuration Examples
High Accuracy Stack
{
"skills": ["image-analyzer", "hf-image-detector", "hive-api"],
"votingStrategy": "majority"
}
Privacy-Focused Stack
{
"skills": ["image-analyzer", "hf-image-detector"],
"externalAPIs": false
}
Fast Detection Stack
{
"skills": ["hive-api"],
"cacheResults": true
}
For video detection, see VIDEO_DETECTION.md.
Usage Guidance
Before installing, verify the following: 1) Ask the publisher for a source repo or homepage and versioned releases—avoid running npm install on unknown scoped packages without reviewing their code. 2) Confirm how Hive Moderation or other cloud APIs are authenticated (the skill should declare required env vars like HIVE_API_KEY); never paste production credentials into an untrusted skill. 3) Be cautious with reverse image search or cloud-based moderation—these will upload images and could leak sensitive content. 4) If you need privacy, prefer the 'Privacy-Focused Stack' but still inspect the local npm packages for telemetry or build-time scripts. 5) Run installs in a sandbox, pin package versions, and review the packages' maintainers and license. If the publisher cannot provide a repository, clear credential-handling guidance, and package provenance, treat this skill as higher risk.
Capability Analysis
Type: OpenClaw Skill
Name: image-detection
Version: 1.0.0
The skill bundle describes legitimate image detection functionalities and provides standard installation instructions using `npm install`. There is no evidence of intentional harmful behavior, data exfiltration, backdoors, or prompt injection attempts against the AI agent within the provided `_meta.json` or `SKILL.md` files. The `npm install` commands are presented as user-facing installation steps, not as commands for the agent to execute during its operation, and the content is purely descriptive and instructional.
Capability Assessment
Purpose & Capability
The SKILL.md describes both local analysis and a cloud-based Hive moderation API, which matches the stated purpose. However the registry metadata claims no install steps, no required env vars, and no primary credential, which is inconsistent with a skill that integrates with external APIs and third-party npm packages.
Instruction Scope
Runtime instructions tell the agent to npm install several scoped packages and to integrate with the Hive Moderation REST API and reverse-image-search (which may upload images). The SKILL.md does not specify how API credentials should be provided or protected, nor does it limit what images may be sent to external services—this can lead to unintended data exfiltration.
Install Mechanism
There is no formal install spec in the registry, but SKILL.md instructs running npm install for scoped packages (@clawhub/* and @raghulpasupathi/*). Installing arbitrary npm packages at runtime is moderate risk: packages can execute code during install and are from unknown publishers. No pinned versions, checksums, or well-known release hosts are provided.
Credentials
The metadata declares no required environment variables or primary credential, yet the Hive API and some model hubs typically require API keys/tokens. This omission is a red flag—credentials are necessary for cloud services but are not declared or explained.
Persistence & Privilege
The skill does not request always: true and has no declared system-wide persistence or privileges. It appears to be user-invocable and not forced into every agent run.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install image-detection - After installation, invoke the skill by name or use
/image-detection - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of image-detection skill, providing multiple methods for AI-generated image detection:
- Introduces three detection skills: local analyzer, HuggingFace ML-based detector, and Hive Moderation API.
- Supports EXIF metadata extraction, artifact detection, and reverse image search integration.
- Offers local-only and privacy-focused detection options with no external API calls.
- Enables high-accuracy, fast, and multi-purpose cloud-based analysis (including NSFW filtering).
- Includes example configuration stacks for different detection needs.
Metadata
Frequently Asked Questions
What is Image Detection?
Analyzes images to detect AI generation, extract metadata, identify artifacts, and perform content moderation using local and cloud-based tools. It is an AI Agent Skill for Claude Code / OpenClaw, with 837 downloads so far.
How do I install Image Detection?
Run "/install image-detection" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Image Detection free?
Yes, Image Detection is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Image Detection support?
Image Detection is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Image Detection?
It is built and maintained by raghulpasupathi (@raghulpasupathi); the current version is v1.0.0.
More Skills