mind-security

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.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "mind-security" with this command: npx skills add Canvinus/mind-security

mind-security

AI security toolkit with four active modules.

Quick Reference

TaskCommandDocs
Deepfake detectionpython3 scripts/check_deepfake.py <path_or_url>deepfake-detection.md
Prompt injection scanpython3 scripts/check_prompt_injection.py "<text>"prompt-injection.md
Malware/phishing scanpython3 scripts/check_malware.py "https://..."malware-scanning.md
AI text detectionpython3 scripts/check_ai_text.py "<text>"ai-text-detection.md

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

Env VarUsed ByRequiredGet It
BITMIND_API_KEYDeepfake detectionFor API modeapp.bitmind.ai/api/keys
GPTZERO_API_KEYAI text detectionYesgptzero.me/dashboard
VIRUSTOTAL_API_KEYMalware scannerOptionalvirustotal.com
URLSCAN_API_KEYMalware scannerOptionalurlscan.io
GOOGLE_SAFE_BROWSING_KEYMalware scannerOptionalconsole.cloud.google.com

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

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Security

Session Password

Provides secure session authentication using bcrypt-hashed passwords, security questions, email recovery, and lockout protection with audit logging.

Registry SourceRecently Updated
Security

agent-bom registry

MCP server security registry and trust assessment — look up servers in the 427+ server security metadata registry, run pre-install marketplace checks, batch...

Registry SourceRecently Updated
Security

agent-bom scan

Security scanner for AI infrastructure — discovers MCP clients and servers, checks packages for CVEs (OSV, NVD, EPSS, KEV), maps blast radius, and generates...

Registry SourceRecently Updated
0128
Profile unavailable