PurpleLlama (Meta)

Comprehensive set of tools to assess and improve LLM security. Includes Llama Guard safety classifiers, CyberSec Eval benchmarks, and Prompt Guard for prompt injection detection. BSD-3-Clause licensed.

View on GitHub Unknown

Guide pending

We haven't written this guide yet.

Guides are drafted from the project's own README and metadata. Until one exists, check the product's repository and documentation for authoritative information.

Nearby on the map

Related projects

Garak (NVIDIA)

NVIDIA/garak

The LLM vulnerability scanner. Probes models for hallucinations, data leakage, prompt injection, misinformation, toxicity, and jailbreaks. Extensive plugin-based architecture with 100+ vulnerability probes. Apache 2.0 licensed.

unknown unknownactivity unknown

Promptfoo

promptfoo/promptfoo

Open-source LLM evaluation and red teaming framework. Test prompts, agents, and RAGs with automated security vulnerability scanning, side-by-side model comparison, and CI/CD integration. Now part of OpenAI. MIT licensed.

unknown unknownactivity unknown

DeepTeam (Confident AI)

confident-ai/deepteam

Red teaming framework for LLM systems with 50+ vulnerabilities, 20+ adversarial attacks, and production-ready guardrails. Includes OWASP, NIST, and MITRE ATLAS framework mappings. Apache 2.0 licensed.

unknown unknownactivity unknown

SkillSpector (NVIDIA)

NVIDIA/SkillSpector

Security scanner for AI agent skills that detects vulnerabilities, malicious patterns, and security risks. Apache 2.0 licensed.

unknown unknownactivity unknown

ADR (Uber)

uber/ADR

Enterprise security system for AI agents providing telemetry collection, benchmark evaluations, and threat detection. Apache 2.0 licensed.

unknown unknownactivity unknown

SafetyCard

safetycard/safetycard

Safety-check MCP servers and AI agents against the OWASP agentic Top 10, and get the safest setup to run them. MIT licensed.

unknown unknownactivity unknown