A robust FastAPI-based service for identifying sensitive words, typos, and linguistic inconsistencies in text.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install hj-check-test
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install hj-check-test using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Sensitive Content Detection API?
This skill provides a comprehensive text auditing solution designed to ensure content safety and linguistic accuracy. By integrating this into Openclaw Skills, developers can programmatically scan text for sensitive vocabulary, common spelling errors, and industry-specific standardized expressions. It functions as a middleware layer that connects to an upstream safeguard API, offering a streamlined RESTful interface for AI agents and applications that require high-integrity content processing.
Sensitive Content Detection API Use Cases
- Real-time moderation of user-generated content in chat applications.
- Automated proofreading and typo correction for documentation and publishing workflows.
- Compliance checking against specific sensitive word lists for regulated industries.
- Enhancing AI agent safety by filtering inputs and outputs through Openclaw Skills protocols.
How Sensitive Content Detection API Works
- The user or agent sends a POST request containing the text content and a userKey to the /api/safeguard/check endpoint.
- The FastAPI service processes the request and forwards the payload to the configured upstream safeguard API.
- The system analyzes the text for three primary categories: sensitive keywords, spelling mistakes, and expression violations.
- The API generates a structured JSON response detailing every error found, including its exact character position, the erroneous term, suggested corrections, and severity levels.
- The calling application uses this data to either flag, block, or automatically correct the content.
Sensitive Content Detection API Setup
Ensure you have Python 3.11+ installed. Follow these steps to deploy the skill:
- Install the required dependencies:
pip install -r requirements.txt
Configure your environment variables in a .env file, specifically setting the SAFEGUARD_API_URL and PORT.
Start the service:
python main.py
- Access the interactive API documentation at http://localhost:8080/docs to test endpoints.
Sensitive Content Detection API Data Schema & Taxonomy
The API returns a structured JSON object with the following schema for detected issues:
| Field | Type | Description |
|---|---|---|
code |
integer | Response status (0 for success, 1 for failure) |
content |
array | List of detected issues |
wrongTerm |
string | The identified sensitive or incorrect word |
expectTerms |
array | Suggested corrections or standard terms |
errLevel |
integer | Severity level of the detected issue |
sentence |
string | The specific sentence containing the error |
Sensitive Content Detection API Advanced Features
- Custom sensitiveCodeList filtering to target specific types of content violations.
- Integrated Swagger UI for real-time API testing and developer onboarding.
- Robust logging system located in logs/app.log for auditing and debugging upstream API performance.
- Configurable API timeouts and environment-based port mapping for cloud deployment.
- Native support for asynchronous requests to handle high-concurrency text scanning within Openclaw Skills environments.
SKILL.md
Loading
Related Openclaw Skills
Sensitive Content Detection API
A FastAPI-powered service designed to identify sensitive keywords, typos, and linguistic compliance issues in text for AI agents.
GoPlus AgentGuard
An AI agent security framework that automatically blocks dangerous commands, prevents data exfiltration, and audits skills for vulnerabilities.
Sue
A comprehensive AI agent skill for evaluating, preparing, and navigating the complexities of lawsuits and legal disputes.
Funnel
Funnel is an AI agent skill designed to diagnose, build, and optimize end-to-end marketing and sales conversion paths for growth-oriented businesses.
AetherCore
A security-focused high-performance JSON optimization and universal smart indexing engine designed for Openclaw Skills.
Organizer
A professional framework for turning cluttered information into structured, navigable, and actionable systems.