Llm Security Python Packages

nemoguardrails

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

llm-guard

The Security Toolkit for LLM Interactions

argus-redact

Encrypt PII, not meaning. Locally.

garak

the LLM vulnerability scanner

giskard

🐢 Open-Source Evaluation & Testing library for LLM Agents

agent-bom

Open security scanner for AI supply chain and infrastructure: agents, MCP, containers, cloud, GPU, and runtime with blast-radius analysis.

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+.

vaara

Adaptive AI Agent Execution Layer — risk scoring, audit trails, regulatory compliance (EU AI Act Article 14)

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.

sunglasses

Sunglasses for AI agents. Protection layer + neighborhood watch.

axonflow

Official Python SDK for AxonFlow — runtime control, MCP policy enforcement, approvals, and audit trails for production AI

xsafeclaw

XSafeClaw - Keeping Your Claw Safe. Real-time monitoring and security for OpenClaw, Hermes, and nanobot AI agents.

signet-sign

Capability-based safety gates for LLM agents. The model proposes; signet authorizes.

hexlock

Format-preserving redaction for PII and sensitive data that works with LLMs/text-based pipelines

medusa-security

AI-first security scanner with 76 analyzers, 9,600+ detection rules, and repo poisoning detection for AI/ML, LLM agents, and MCP servers. Scan any GitHub repo with: medusa scan --git user/repo

armorer-guard

Fast local Rust scanner for AI-agent prompt injection, credential leaks, exfiltration, and risky tool calls

mcp-audit-scanner

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

projectair

Project AIR: forensic reconstruction and incident response for AI agents. Signed AgDR decision records, OWASP ASI01-ASI10 detection, signed forensic evidence exports.

shisad

Security-first AI agent daemon — the model proposes actions, the runtime decides what execute

q-uestionable-ai

Agentic AI Security Research

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.

agentic-radar

A security scanner for your LLM agentic workflows

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.

cyberscanai

AI Agent Tool for Penetration Testing and Network Forensics