Spaces:
Sleeping
Sleeping
|
Download README.md from Safe-Harbor/harbormaster: direct link, hf CLI and curl.
- Browser
- Download file 1.29 kB
-
https://huggingface.co/spaces/Safe-Harbor/harbormaster/resolve/main/README.md
- Command line
-
hf download hf://spaces/Safe-Harbor/harbormaster/README.md
-
curl -L -o README.md https://huggingface.co/spaces/Safe-Harbor/harbormaster/resolve/main/README.md
1.29 kB
A newer version of the Streamlit SDK is available: 1.67.0
metadata
title: Harbormaster
emoji: π
colorFrom: blue
colorTo: indigo
sdk: streamlit
sdk_version: 1.42.0
app_file: app.py
pinned: false
license: mit
short_description: DEMO Lightweight security tool protects models from threats
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
π‘οΈ Harbormaster: AI Model Security Demo
Harbormaster is a lightweight security tool that protects your Hugging Face models from common vulnerabilities and threats. This demo showcases real-time protection features including:
- π Prompt injection detection
- π Data leakage prevention
- β‘ Rate limiting controls
- π Token validation
- π Security monitoring
Try it out by entering different prompts to see how Harbormaster identifies and blocks potential security threats while allowing safe interactions to proceed.
Quick Start
- Enter a Hugging Face model ID
- Input your test prompt
- Click "Run with Protection" to see security analysis
About
Developed by Safe Harbor Cybersecurity to make enterprise-grade AI security accessible to the broader Hugging Face community. Our mission is to help developers deploy AI models safely and securely.