name: mind-security description: > AI security toolkit — deepfake detection, prompt injection scanning, malware/phishing URL scanning, and AI text detection. Use when: (1) verifying if an image, video, or audio is a deepfake or AI-generated, (2) scanning user inputs for prompt injection attacks, (3) scanning URLs for malware, phishing, or domain reputation threats, (4) determining if text was written by an LLM. metadata: {"openclaw": {"emoji": "🛡️", "requires": {"bins": ["python3"], "anyBins": ["curl", "wget"]}, "homepage": "https://github.com/mind-sec/mind-security"}}

mind-security

AI security toolkit with four active modules.

Quick Reference

Modules

Deepfake detection — BitMind API (Bittensor Subnet 34) for images and videos. Supports YouTube, Twitter/X, TikTok URLs. EXIF/metadata fallback for local images. Set BITMIND_API_KEY (get key).

Prompt injection — Multi-layer: 50+ regex patterns (instant, zero-dep) + LLM Guard ML scanner (optional, pip install llm-guard). Detects DAN jailbreaks, prompt extraction, context manipulation, and novel attacks.

Malware/phishing scanning — VirusTotal (70+ engines), URLScan.io (1500+ brands), Google Safe Browsing, plus local heuristics (typosquatting, suspicious TLDs, phishing patterns). Works with no keys via heuristics.

AI text detection — GPTZero API with per-sentence scoring and ~99% accuracy across GPT-4/5, Claude, Gemini, LLaMA. Requires GPTZERO_API_KEY (get key).

API Keys

Script Conventions

• python3 scripts/<script>.py --help
• Core: zero pip dependencies (stdlib only)
• Optional ML: pip install llm-guard for prompt injection Layer 2
• JSON to stdout, errors to stderr
• Exit 0 success, exit 1 failure