|
Sentinel — AI Agent Security | Prompt Injection Defence
Sentinel v0.9.0 detects and blocks prompt injection attacks, encoding bypasses, and credential exposure in AI agents. 2,293 tests. LangChain, CrewAI, Haystac...
|
85 % |
|
Sunglasses | The Input Firewall for AI Agents | Open Source AI Agent Security
Sunglasses is an open source filter that blocks prompt injection and MCP tool poisoning before it reaches your AI agent. Local first, MIT licensed.
|
84 % |
|
Swarms Network - Multi-Agent AI Certification
RSCT certification for multi-agent AI systems. Ensure safety, detect hallucinations, prevent prompt injection.
|
83 % |
|
Shieldon — Audit AI Agent Skills Before Execution
Security scanner for AI agent skills. 39 YARA rules across 6 threat categories plus an LLM semantic layer. For individuals installing skills and agentic fram...
|
83 % |
|
AI Agent Shields — Free AI Agent Security Scanner
Free AI agent security scanner and supporting tools for permissions, prompts, credentials, browser access, network access and governance.
|
83 % |
|
NeuroSec.ai — AI and Agent Security, Unified
NeuroSec secures both AI models and autonomous agents with runtime threat detection, host-level enforcement, and audit-ready governance.
|
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 % |
|
Network-AI | Multi-Agent Orchestration for Production Systems
Network-AI is a TypeScript/Node.js multi-agent orchestration layer with shared-state locking, permission gating, audit trails, FSM governance, and 32 framewo...
|
82 % |
|
Sentinel Gateway — Structural AI Agent Security
Token-gated enforcement for autonomous AI agents. The only solution that enforces at the execution layer, not the reasoning layer.
|
82 % |
|
AgentShield — Open-Source Prompt Injection Detection for AI Agents
Open-source security middleware for AI agents and RAG pipelines. Detect prompt injection attacks using ZEDD, monitor embedding drift, and gain threat intelli...
|
82 % |
|
Manetu AgentVisor™
Controlled Autonomous Runtime Environment — Confinement and Observability for AI agents.
|
82 % |
|
AgentSkin | Clean Context Before Inference
AgentSkin is fidelity-first context middleware for AI agents. Remove tool noise before it reaches model context.
|
82 % |
|
AgentCop — AI Agent Security Scanner
Free AI agent security scanner. Real AST taint analysis, OWASP LLM Top 10 coverage, CWE-mapped findings. Scan LangGraph, CrewAI, AutoGen, OpenClaw agents. No...
|
82 % |
|
ShellFrame AI — Security infrastructure for AI agents
Let AI agents use credentials without seeing them. Scan exposed paths locally, then enforce identity, policy, approvals, and audit with ShellFrame AI.
|
82 % |
|
WatchMyAgents — Cybersecurity for AI Agents
Detect abnormal behavior, prevent compromise and enforce adaptive per-agent security policies for AI agents in production.
|
82 % |
|
AgentFlow — AI-Native Communication Intelligence
|
82 % |
|
AgentScan - AI Agent & LLM Security Scanner
Automated security scanning for AI agents and LLMs. 412 attack vectors across 19 categories. Prompt injection, data exfiltration, jailbreak, MCP poisoning, R...
|
82 % |
|
Magesh Dhanasekaran — Agentic AI & PQC
Senior Security Consultant at AWS. Building and securing agentic AI and PQC platforms. Exploring robotics and physical AI. Views my own.
|
82 % |
|
AgentSecOps — AI Agent Security Assessments & Hardening
AI-agent security readiness assessments for teams using coding agents, MCP servers, RAG bots, and autonomous workflows. Reduce the blast radius of prompt inj...
|
82 % |
|
Scanwise.dev — Website Vulnerability Scanner & AI Code Fixes
External website vulnerability scanner — checks DNS, TLS, exposed secrets, and security headers, then generates AI code fixes. First scan free; pay-as-you-go...
|
82 % |
Detected social media networks