Search Packages

llm-guard

The Security Toolkit for LLM Interactions

skylos

Open-source PR gate for Python, TS/JS, Java, and Go. Stop merging dead code, secrets, security flows, and AI-code regressions.

agentdojo

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

mcpsafetywarden

MCP servers expose tools with no information about what they actually do at runtime. mcpsafetywarden sits between your agent and any MCP server, profiling tool behavior, blocking destructive calls, and running active security audits before you trust them in a workflow.

xsafeclaw

Introducing XSafeClaw: The Open-Source Agent Safety Platform from Fudan University

sunglasses

Sunglasses for AI agents. Protection layer + neighborhood watch.

q-uestionable-ai

Agentic AI Security Research

navi-sanitize

Deterministic input sanitization for untrusted text — invisible characters, homoglyphs, and encoding tricks, handled before your code sees them. Zero dependencies, no ML. Python 3.12+.

pytector

Easy to use LLM Prompt Injection Detection and Prompt Input Sanitization / Detector Python Package with support for local models, API-based safeguards, and LangChain guardrails.

aig-guardian

🛡️ Open-source LLM security library for Python. Protect your AI apps from prompt injection, data leakage, and harmful outputs in 3 lines of code.

agentseal

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP servers for tool poisoning.

agent-aegis

LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One line, zero code changes.

humanbound-cli

DEPRECATED: renamed to 'humanbound'. This is the final release; no further updates will be published.

wauldo

Official Python SDK for Wauldo — verified AI answers with zero hallucinations. pip install wauldo

mcp-audit-scanner

Security scanner for MCP (Model Context Protocol) server configurations. Detects prompt injection, credential exposure, supply chain risks, and more.

arc-sentry

Whitebox prompt injection detector for self-hosted open-weight LLMs. Deployment-specific behavioral monitor; calibrates on your traffic, detects drift from that baseline.

mvar-security

MVAR: Information Flow Control for LLM Agent Runtimes

sovereign-shield

AI security framework: deterministic Immutable input filtering, adaptive rule learning, optional LLM veto verification. Zero dependencies. Works without an LLM. Patent Pending.

clawzero

Deterministic execution boundary for AI agents. IFC enforcement at the sink. 5 frameworks. 50 attack vectors. Apache 2.0.

promptguard-sdk

PromptGuard Python SDK — Drop-in security for AI applications

anthale

Anthale's official Python SDK

agentshield-guard

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

llm-injection-guard

Drop-in prompt injection defense for LLM apps and AI agents — detect, sanitize, block, and audit injection attacks in real time. Includes multi-turn session scanning, allow-lists, rate-abuse detection, multi-layer scanner, FastAPI and Flask middleware.

pyaigis

The open-source firewall for AI agents. Block prompt injections, jailbreaks, and data leaks before they reach your LLM. Multi-layer defense, agent-era security (MCP/Capability), US/CN/JP/EU compliance. Zero-dependency core.