|
Declawed - AI Security Scanner
Scan AI skills, prompts, MCP servers, and agent configurations for malicious content, prompt injection, and security vulnerabilities.
|
84 % |
|
ClawHeart Desktop · Local AI Security Gateway
Local-first proxy, interception, and audit for AI Agents. Three monitoring tiers × eight defense layers × six tool pages — make every call observable, blocka...
|
84 % |
|
Agent Armor - AI Agent Security Framework
Open-source security framework that detects and defends against AI Agent Traps. Content injection, jailbreaks, RAG poisoning, exfiltration, and more.
|
83 % |
|
1Claw — Secret Management for AI Agents
HSM-backed secret management for AI agents and humans. MPC key splitting across GCP, AWS, and Azure. Vault API, MCP server, Shroud TEE proxy, Intents API for...
|
83 % |
|
SkillsSafe — Free AI Skill Security Scanner | Check Before You Install
Free security scanner for AI agent skills. Scan any SKILL.md, MCP config, or system_prompt for credential theft, data exfiltration, and prompt injection. Sup...
|
82 % |
|
Mirror Security | Fully Homomorphic Encryption for AI
Mirror Security brings fully homomorphic encryption to AI. Encrypt inference with VectaX, red-team with DiscoveR, and govern every agent with AgentIQ.
|
82 % |
|
Nox — The security scanner that understands your AI app
Open-source security scanner with first-class AI app security: prompt injection at the call site, embedding leakage, agent over-privilege, MCP hardening, cro...
|
82 % |
|
SKVault — skscan: Security Scanner for AI Agent Skills
Open-source security scanner for AI agent SKILL.md files. Catches prompt injection, secret leaks, dangerous code, and hidden instructions before they run.
|
82 % |
|
Crusty Security — Security Monitoring for OpenClaw Agents
Malware scanning, skill auditing, threat intelligence, and continuous monitoring — protecting your OpenClaw AI agents from malicious skills, prompt injection...
|
82 % |
|
UltraSushiTron - Your AI. Your Secrets. Your Control.
Your AI. Your Secrets. Your Control. UltraSushiTron is a security-first AI agent framework with user-approved secret access.
|
82 % |
|
ShieldPilot — Secure Every AI Agent Before It Ships
The only open-source security platform with ML-powered injection detection, MCP vulnerability scanning, and supply chain auditing. 209+ attack patterns. Zero...
|
82 % |
|
LYNX Security Systems — Enterprise Server Protection & Recovery
Automated Fernet-encrypted backups, zero-trust password authentication, and instant disaster recovery for Discord servers.
|
82 % |
|
AgentShield - The Security Audit for Your AI Agents
Open-source security audit for your AI agents: the skills they run, exposed secrets, risky MCP config, and unsafe updates. Runs on your machine.
|
82 % |
|
ShieldAi | AI Security Layer for Autonomous Crypto Agents
AI Security Layer for Autonomous Crypto Agents
|
82 % |
|
SecureSkill — Know what a skill does before it runs
SecureSkill is the security layer for the Agent Skills open standard — calibrated for OpenClaw, Claude, Hermes, OpenAI Codex, and Cursor. Independent third-p...
|
82 % |
|
SkillOx — Trust the skills your AI agents run
Audit any SKILL.md before installing it. Free, in your browser, in under 30 seconds.
|
82 % |
|
Protected Labs - Offensive Security for AI-Coded SaaS
Protected Labs secures high-velocity, AI-assisted SaaS teams. Senior engineers hunt the logic flaws and critical exploits that automated scanners miss.
|
82 % |
|
SecureSkill — Know what a skill does before it runs
SecureSkill is the security layer for the Agent Skills open standard — calibrated for OpenClaw, Claude, Hermes, OpenAI Codex, and Cursor. Independent third-p...
|
82 % |
|
Ambient Authority: enterprise AI security, independently reported
Independent, vendor-neutral reporting on enterprise AI security: prompt injection, agent security, model supply chain, and AI governance.
|
82 % |
|
@zfuzz/mcp — Security Copilot for AI Coding Agents
The security tool that plugs into your AI coding agent (Cursor, Claude Code, Codex…). It catches vulnerabilities, leaked secrets and dangerous libraries whil...
|
81 % |
Detected social media networks