Search
safepropel
charan6366
SafePropel Framework - Unified Protection System for AI Workflow Execution with 4-layer security (Compilation, Encryption, Runtime Engine, Firewall)
...moremcpnewcli
mcpnew Contributors
Scaffold secure-by-default MCP servers (TypeScript or JavaScript) with deny-all permissions, typed tool stubs, and audit hooks pre-wired.
...morepromptwall
tharvid
Lightweight runtime security for LLM apps — block prompt injection, jailbreaks, and data exfiltration (PII/PHI/PCI) before they reach your model
...moretibet-ai-sbom
Jasper van de Meent <[email protected]>, "Root AI (Claude)" <[email protected]>
BSI/G7 SBOM-for-AI implementation — software, models, datasets, infrastructure, security, KPIs. With TIBET provenance + CBOM evidence linkage.
...moreAgenvoy
pardnchiu
A Go-based Agentic AI framework with skill routing, multi-provider intelligent dispatch, and security-first shared agent design
...more@westbayberry/dg
comcat01
Supply chain security scanner for npm and Python dependencies — detects malicious packages, typosquatting, dependency confusion, and 26+ attack patterns
...moreghostpatch
jaysheen
AI-powered security vulnerability scanner that runs locally via npm with zero infrastructure. Uses free HuggingFace models by default.
...moreaiagentshield
vmgs-ruri
Security scanner for AI Agents and MCP Servers — 10 scanners for prompt injection, supply chain poisoning, secret leaks, and misconfigs
...moremindmesh-ai
Multi-provider AI orchestration for Claude Code — review, security audit, and analysis via OpenAI, Gemini, Z.ai, Ollama
crypto-shuffle
makaretu
Cryptographically secure shuffle using the Fisher-Yates algorithm. The browser's (or NodeJS) crypto services are used to generate strong random numbers.
...moreio.github.node-man/dechonet-mcp
GitHub Actions
13 security recon tools for AI agents — DNS, SSL, HTTP, email, ports, ASN. Health Score 0-100.
resksecure
RESK Security
Bitmask-based LLM security firewall with policy-driven logits filtering using GPU-accelerated Aho-Corasick pattern matching
...morereverse-engineering-pro-max
amantapradipa
AI-powered intelligence for deep system analysis, code decompilation, architecture inference, network traffic analysis, and security reverse engineering.
...moreskill-lint
lich_amnesia
Security linter for Claude Code / agent skills. Detects prompt injection, obfuscation, credential exfiltration, and other toxic patterns before you install a skill.
...moremcp-wsl-exec
spences10
A secure Model Context Protocol (MCP) server for executing commands in Windows Subsystem for Linux (WSL) with built-in safety features and validation
...moreautoai-agentwatch
autoailabsuk
AI Agent Observability & Security — MCP server for tracing reasoning chains, tracking costs, detecting hallucinations, and monitoring agent behavior
...more@voratiq/sandbox-runtime
voratiq
(Voratiq-maintained fork of the) Anthropic Sandbox Runtime (ASRT) - A general-purpose tool for wrapping security boundaries around arbitrary processes
...more@cyber-sec.space/ai-auth-gateway
aka21
A Model Context Protocol (MCP) Proxy Gateway for secure AI tool execution, built with TypeScript, RBAC, and OS Keychain integration.
...more@blockxai/evi-sdk
blockxai
EVI SDK — AI-powered smart contract development platform with wallet deployment, security auditing, compliance validation, and blockchain verification
...morewsl-exec-mcp
dhruv kejriwal
A secure Model Context Protocol (MCP) server for executing commands in Windows Subsystem for Linux (WSL) with built-in safety features and validation
...more