ai-agent-security

Here are 18 public repositories matching this topic...

always-further / nono

Kernel-enforced agent sandbox. Capability-based isolation with secure key management, atomic rollback, cryptographic immutable audit chain of provenance. Run your agents in a zero-trust environment.

security mcp code-execution ai-agents zero-trust ai-security runtime-security supply-chain-security sigstore agent-sandbox prompt-injection llm-security llm-sandbox ai-security-tool agent-security mcp-security ai-agent-security ai-agent-sandbox

Updated
Rust

openguardrails / openguardrails

Star

Protect every action your agent takes.

guardrails prompt-injection data-leakage-prevention llm-safety ai-gateway content-safety ai-agent-security ai-security-gateway enterprise-ai-guardrails openclaw openclaw-security

Updated
TypeScript

InnerWarden / innerwarden

Star

Autonomous open-source security agent for Linux (Apache-2.0). 40 eBPF hooks, 49 detectors, 208 Sigma rules, MITRE ATT&CK coverage, AI agent protection, mesh defense.

linux rust security opensource kernel honeypot firewall incident-response intrusion-detection ebpf yara anomaly-detection threat-detection apache-2 sigma-rules host-security ai-agent-security correlation-engine autonomous-defense agent-guard

Updated
Rust

👁 clawsecure-openclaw-security

ClawSecure / clawsecure-openclaw-security

Star

Free OpenClaw security scanner. 2,890+ agents audited. 3-Layer Audit Protocol. OWASP ASI 10/10 coverage. AI agent integrity layer.

security-automation runtime-verification vulnerability-scanner malware-detection supply-chain-security ai-agent ai-agent-security owasp-asi prompt-injection-detection agentic-security openclaw openclaw-security ai-security-scanner ai-agent-audit security-clearance-api ai-skill-scanner openclaw-audit agent-integrity clawhavoc ai-agent-vulnerability

Updated

dormstern / leashed

Star

AI got hands. This is the leash. Policy, audit, kill switch for any AI agent with access to your accounts.

typescript devtools npm-package devin audit-log browser-automation ai-safety policy-engine kill-switch claude ai-security ai-agent llm-security ai-agent-security agent-governance openclaw credential-safety anchorbrowser

Updated
TypeScript

Acacian / aegis

Star

Policy CI/CD for AI agents — aegis plan + aegis test for AI agent security. Auto-instruments 11 frameworks. No infra required.

mcp compliance ai-safety policy-engine ai-agents audit-trail ai-security policy-as-code guardrails pii-detection policy-testing ai-governance langchain prompt-injection llm-security model-context-protocol agent-security mcp-security ai-agent-security selection-governance

Updated
Python

No-Box-Dev / Noxkey

Star

macOS secrets manager with Touch ID. Stores API keys in the Keychain, detects AI agents, delivers secrets via encrypted handoff. Free, open source, local-only. A dotenv alternative for developers.

macos cli open-source encryption mcp keychain developer-tools touch-id swiftui secrets-manager menu-bar-app credential-management ai-agent-security dotenv-alternative

Updated
JavaScript

Meisterware / openpakt-spec

Star

OpenPAKT: Open Protocol for Agent Knowledge Trust — a language-agnostic specification for AI agent security findings, scenarios, and CI policy gating.

json-schema sarif devsecops ai-agents open-standard ai-security security-scanning ci-security llm-security agent-security ai-agent-security security-standard openpakt security-spec detektor

Updated

mustafadakhel / oag

Star

Portable runtime policy and audit layer for AI agents - HTTP/HTTPS proxy enforcing egress policies, inspecting content, materializing secrets, and recording every decision.

proxy-server policy-engine ai-agents ai-security guardrails prompt-injection ai-gateway llm-firewall agent-security ai-agent-security agent-governance agent-guardrails egress-proxy

Updated
Kotlin

fishnetproxy / fishnet

Star

Security proxy for AI agents (OpenClaw, LangChain, CrewAI). Protects API keys, enforces spend limits, blocks dangerous endpoints. Local-first Rust binary — your credentials never leave your machine.

rust rate-limiting ai-safety local-first credential-vault eip-712 zk-proofs llm-security defi-security crypto-wallet-security ai-agent-security security-proxy openclaw api-key-proxy spend-limits

Updated
Rust

EaCognitive / agentgate

Sponsor

Star

AI agent runtime governance control plane: intercept tool calls with PII protection, approvals, and formal verification.

cybersecurity formal-verification governance ai-security audit-logging policy-as-code llm-security ai-gate genai-security mcp-server-security ai-agent-security pii-protection ai-runtime-security ai-agent-governance

Updated
Python

DzikPasnik / x402Guard

Star

Non-custodial x402 safety proxy & guardrails engine for autonomous AI agents in DeFi — spend limits, contract whitelists, session keys (EIP-7702) on Base & Solana

rust security typescript proxy nextjs ethereum web3 base evm ai-agents solana defi blockchain-security guardrails non-custodial eip-7702 elizaos x402 ai-agent-security session-keys

Updated
TypeScript

NAdrian95 / ai-agent-security-checklist

Star

Comprehensive security checklist for deploying autonomous AI agents safely. Covers prompt injection, data exfiltration, tool-use safety, and autonomous execution risks.

checklist security mcp autonomous-agents ai-safety ai-agents llm prompt-injection llm-security ai-agent-security

Updated

thebasedcapital / pfw

Star

Package Firewall — self-hosted supply chain security for macOS. Intercepts npm/pip/cargo/yarn in ALL shells including AI agents. 4 vuln sources (OSV + GHSA + deps.dev + CISA KEV). Zero telemetry.

macos security package-manager firewall self-hosted cve osv sca devsecops vulnerability-scanner malware-detection lulu dependency-security supply-chain-security ai-agent-security npm-security zero-telemetry supply-chain-attack pip-security cargo-security

Updated
TypeScript

ClawSecure / openclaw-developer-tools

Star

Free OpenClaw developer tools by ClawSecure. Security, orchestration, and productivity tools for AI agents. MIT-licensed, free forever.

nodejs open-source typescript workflow-engine developer-tools ai-agents free-tools agent-orchestration ai-agent-security openclaw openclaw-skills openclaw-extension openclaw-security openclaw-tools clawsecure

Updated

agentguard-ai / tealtiger-python-prod

Star

TealTiger Python SDK - Drop-in security and cost tracking for OpenAI, Anthropic, and Azure OpenAI

agent security audit policy openai compliance governance ai-agents claude llm langchain anthropic ai-agent-security

Updated
Python

edimuj / vexscan

Star

Security scanner for AI agent plugins, skills, MCPs, and configurations. Detects prompt injection, malware, credential theft, and obfuscated payloads.

malware-detection ai-security-tool ai-agent-security clawdbot clawdbot-security

Updated
Rust

SecAI-Hub / mcp-firewall

Star

Default-deny enterprise MCP gateway with signed policy bundles and taint tracking

proxy mcp firewall policy-engine model-context-protocol mcp-security prompt-injection-defense ai-agent-security

Updated
Go

Improve this page

Add a description, image, and links to the ai-agent-security topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the ai-agent-security topic, visit your repo's landing page and select "manage topics."

Learn more

URL: https://github.com/topics/ai-agent-security