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

datafog

Offline PII firewall for AI agents and LLM apps: fast local detection and redaction, Claude Code hook, LiteLLM guardrail. Zero network calls, one dependency.

giskard

🐢 Open-Source Evaluation & Testing library for LLM Agents

vaara

Open-source evidence layer for AI governance. Gates every AI agent tool call against your policy and writes a hash-chained execution record an auditor verifies offline, without trusting the operator. Root-agnostic, and binds to a TPM 2.0 or SEV-SNP hardware root when present. Your environment, no SaaS, no telemetry. AGPL-3.0.

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+.

assay-it

Policy-as-code for MCP agents: deny risky tool calls before they run, prove what ran with verifiable evidence, and enforce egress in the kernel (eBPF/LSM, Linux). Deterministic, offline-first, bounded claims.

skilltotal

Scan AI components (MCP servers, agent skills, npm/PyPI packages) for malware & risky capabilities. Local, deterministic, evidence-anchored. Free & OSS.

agentx-security-sdk

Runtime action firewall for AI agents: the keyless Shield. Blocks catastrophic tool calls (DROP TABLE, SSRF, secret exfil) in-process, no key. MIT.

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.

agent-bom

AI supply-chain & cloud security scanner and self-hosted control plane — agents, MCP, packages, cloud estate, non-human identities, and LLM cost. SBOM/SARIF, graph attack-paths, runtime enforcement, and compliance evidence.

veldt-kya

KYA (Know Your Agents) — Open-source trust, governance, and evidentiary assurance infrastructure for autonomous systems. Built on KYP (Know Your Principal), a unified trust model for human users, AI agents, service accounts, and machine identities.

aicu-scanner

Black-box security scanner for LLM applications — prompt injection, safety bypass, credential leakage

sunglasses

Sunglasses for AI agents. Protection layer + neighborhood watch.

medusa-security

AI-first security scanner. NEW in v2026.7: Claude Code compromise detection — vet .claude/ hooks, permissions & skills before you clone — plus an always-on AI attack-signature scanner and native Rust & PHP rules. Also: medusa scan --git to vet any repo, medusa secrets scan for leaked API keys. 40,000+ patterns, zero setup.

agent-audit

Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 51 rules mapped to OWASP Agentic Top 10 (2026). Works with LangChain, CrewAI, AutoGen.

mcp-audit-scanner

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

agentic-radar

A security scanner for your LLM agentic workflows

dfx-agentguard

Autonomous security scanner for AI agents - detects prompt injection, tool abuse, data exfiltration, and all 10 OWASP ASI Top 10 vulnerabilities. MCP server mode included.

crucible-security

pytest for AI agents - Autonomous red-teaming, behavioral monitoring & security testing for LLM agents

immunity-agent

Runtime security for Agents. Blocks dangerous commands, prevent secret leaks, stop prompt injection, gate risky package installs and visibility and control over tool calls.

mcppt

MCPTROTTER - 28 automated security checks for any MCP server