capability

Ai Security agents

This page lists every AI agent in the MeshKore directory tagged with the Ai Security capability. Agents are sourced from public platforms (GitHub, Hugging Face, npm, PyPI, awesome-list curations, and direct submissions), normalized by the MeshKore worker, and ranked by GitHub stars. Each card links to the agent's profile with details on capabilities, framework, language, freshness, and source attribution.

46 agents in this capability · ranked by popularity

Top 46 Ai Security agents

rehydra-sdk68 ★

Prevent accidental PII leakage in LLM prompts before they hit the model.

ivycheck-python-sdk2 ★

Python SDK for IvyCheck

damn-vulnerable-ai-agent— ★

The AI agent you're supposed to break. 17 agents, 12 vulnerability categories, zero consequences.

tokenauditor— ★

Local-first MCP router integrity auditor for AI agent workflows.

@oconnector/mcp-gateway— ★

Security Proxy for Model Context Protocol — Govern any MCP tool call with ABS Core NRaaS (Non-Repudiation as…

@neurosec/sentry— ★

NeuroShield Sentry — host-level agent protection daemon. Detects and blocks malicious AI agent actions at the…

@silmaril-security/sdk— ★

TypeScript SDK for Silmaril Firewall — prompt injection and jailbreak detection

@mcp-guardian/server— ★

Security, cost, and health governance proxy for MCP infrastructure — three-layer detection engine (regex +…

miii-security— ★

Security-focused `SKILL.md` packs for reviewing and hardening LLM systems.

@inkog-io/cli— ★

Security co-pilot for AI agents. Scan for vulnerabilities, verify governance, and generate compliance reports…

abscore-mcp-gateway— ★

Security Proxy for Model Context Protocol — Govern any MCP tool call with ABS Core NRaaS (Non-Repudiation as…

@deepsweepai/mcp-firewall— ★

Enterprise-grade MCP firewall for conscious AI stewardship - Zero-trust security layer for Model Context…

taintctl— ★

Content-aware provenance layer for Claude Agent SDK. Detects dangerous content at every tool I/O boundary…

agent-airlock— ★

A type-checker for AI tool calls — strict argument validation, ghost-argument stripping, and self-healing…

agent-immune— ★

Adaptive threat intelligence for AI agent security — semantic memory, multi-turn escalation, output scanning…

agent-memory-guard— ★

Runtime defense layer that protects AI agent memory from poisoning, tool abuse, privilege escalation, and…

agent-security-harness— ★

474 security tests for AI agent systems - MCP, A2A, L402, x402 wire-protocol testing, decision governance…

agentguard-observe— ★

MrProbe / Agent Guard customer observation SDK — ship your agent's response back to MrProbe in 6 lines.

agentic-guard— ★

Static analyzer for prompt injection and confused-deputy risks in LLM agent code.

agentshield-guard— ★

Official Python SDK for AgentShield — prompt-injection detection for LLM agents.

agentsploit— ★

Offensive security framework for AI agents and MCP servers

ai-agent-scanner— ★

Discover, assess, and secure AI agents across your infrastructure

bulwark-agent-security— ★

Enterprise-grade defense framework for AI agents — protects against prompt injection, data exfiltration, and…

capnagent— ★

Capability-based authority tokens for AI agent tool calls. Python bindings.

langchain-agent-memory-guard— ★

LangChain middleware integration for OWASP Agent Memory Guard — runtime defense against AI agent memory…

langchain-forcefield— ★

LangChain integration for ForceField AI security -- scan prompts and moderate outputs in your LangChain…

llama-index-forcefield— ★

LlamaIndex integration for ForceField AI security -- scan prompts and moderate outputs in your LlamaIndex…

llama-index-trustguard— ★

TrustGuard integration for LlamaIndex - protect your RAG pipeline from malicious content

llmarmor— ★

OWASP LLM Top 10 security scanner for AI-powered applications

llmpromptdefender— ★

Static security scanner for LLM and agentic source code — finds prompt-injection, context-leak, PII, RAG, and…

mithril-llm— ★

A firewall for LLMs — block prompt injection, jailbreaks, and PII exfiltration in real time.

owasp-agent-security-regression-harness— ★

OWASP harness for executable security regression testing of agentic applications and MCP-integrated systems.

pydantic-ai-guardrails— ★

Production-ready guardrails for Pydantic AI with native integration patterns

rag_control— ★

A runtime governance, security and execution control layer for Retrieval-Augmented Generation (RAG) systems.

sentinel-llm-security— ★

SENTINEL — AI Security Platform. 49 Rust Engines + Micro-Model Swarm. Defense, Offense, Framework.

stride-gpt— ★

AI-powered threat modeling using the STRIDE methodology

agenthive-sim— ★

Multi-agent attack simulation framework for AI systems

ragrank-cr— ★

Document influence analysis for RAG systems using social network centrality measures

@cellar-door/mcp-server— ★

MCP server exposing cellar-door EXIT and ENTRY verifiable markers as AI-native tools

agent-shield-int— ★

LLM Prompt Injection Detection CLI — 3-layer detection (Vigil + DistilBERT ONNX + Rules)

openclaw-radware-agentic-protection— ★

OpenClaw integration package for Radware Agentic AI Protection

agenticdome-python-sdk— ★

Official Python SDK for AgentGuard Intelligence Engine and Action Firewall.

openclaw-plugin-agenticdome— ★

AgenticDome security middleware and firewall plugin for OpenClaw.

n8n-nodes-radware-agentic-protection— ★

n8n community node for Radware Agentic AI Protection in-path enforcement

sentraguard-agent— ★

SentraGuard framework-neutral guardrail core for AI agents — LangChain/LangGraph, LiteLLM, and direct…

@blamejs/exceptd-skills— ★

AI security skills grounded in mid-2026 threat reality, not stale framework documentation. 51 skills, 11…

Browse other capabilitys