Search
decoy-tripwire
ad30jone
Security tripwires and local MCP proxy for AI agents. Detect prompt injection and enforce tool-call policy.
shrike-guard
habirua
Shrike Security SDK - Protect your LLM applications (OpenAI, Claude, Gemini) from prompt injection, PII leakage, and jailbreaks
...moremcpsec
robdtaylor
Security scanner for MCP (Model Context Protocol) servers - detects tool poisoning, credential exposure, prompt injection, and SSRF
...morelangchain-axiorank
AxioRank
AxioRank middleware for LangChain agents: govern every tool call and model turn through one Zero-Trust security gateway.
Rag Based Ai Pentest Report Generator
Abhinandan-Khurana
A sophisticated tool that leverages RAG (Retrieval Augmented Generation) to analyze penetration testing data and generate comprehensive security reports.
...more@silker-ai/agent
jarzebowsky_dev
Lightweight runtime security agent for AI-powered apps - detects anomalies, blocks attacks, and provides real-time protection
...moreskillscan-security
Standalone AI skill security scanner — detects prompt injection, tool poisoning, and supply-chain attacks in MCP skills
openclaw-secure
jmwaltman
Hardware-gated secret management for AI agents. Secures OpenClaw API keys with pluggable backends (Keychain, 1Password, Bitwarden, and more).
...more@stranzwersweb2/skillsync-mcp
stranzwersweb2
SkillSync MCP server — search, scan, install & manage Claude Code skills with built-in security scanning and startup verification
...more@agenticensor/algiz
algiz
Algiz security plugin for OpenClaw - detect and defend against agent threats: secret masking, command guard, prompt injection scanner
...moreslowmist/MasterMCP
MasterMCP demonstrates security vulnerabilities in MCP frameworks through practical attack examples, aiding developers in understanding and mitigating potential risks.
...more@soulofzephir/pi-skill-pentesting
soulofzephir
Comprehensive pentesting & security check skill for Pi coding agent - headers, ports, SQLi, XSS, OWASP Top 10
secure-scheduler
kolyaventuri
Secure scheduler is an easy to use module for scheduling events via end-user input using sandboxed method execution.
Vexqr
ghulam36460
Vexqr - Connect any AI (Claude, Gemini, Copilot, Cursor, etc.) to security tools with real-time supervision and MCP integration
...moresentinely
sentinely
Sentinely — Security layer for AI agents. Stop prompt injection, memory poisoning, and agent drift in 3 lines of code.
@thornguard/sdk
jdmay
Embeddable security primitives for MCP server developers — PII redaction, tool poisoning detection, ANSI sanitization, and command injection scanning.
...morehermes-katana
Hermes Katana contributors
Defense-in-depth security toolkit for LLM agents — taint tracking, proxy secret guard, policy engine, and red-team benchmarking
...more@kryptsec/oasis
digitr33
OASIS - Open-source AI security benchmarking CLI. Run LLM penetration testing benchmarks with MITRE ATT&CK analysis.
hippocrates-middleware
achmddfzn
Next.js security middleware with Redis-backed threat scoring, honeypot decoy routing, and Python ML engine for advanced detection.
...morenullsec-guard
trynullsec
Security scanner for AI-generated code. Finds vulnerabilities, gives risk scores, and generates fix prompts for Cursor, Claude, and Codex.
...more