Skip to content
#

generative-ai-security

Star

Here are 7 public repositories matching this topic...

requie / LLMSecurityGuide

Sponsor
Star 147

A comprehensive reference for securing Large Language Models (LLMs). Covers OWASP GenAI Top-10 risks, prompt injection, adversarial attacks, real-world incidents, and practical defenses. Includes catalogs of red-teaming tools, guardrails, and mitigation strategies to help developers, researchers, and security teams deploy AI responsibly.

offensive-security ai-safety red-teaming ai-security prompt-injection llm-security llm-vulnerabilities generative-ai-security-assurance prompt-injection-llm-security ai-security-tool prompt-injection-defense llm-security-compliance-prompt-injection generative-ai-security
  • Updated Apr 3, 2026

ankit-sengupta05 / mesh_guard

Star 2

Self-healing AI agent security framework for LangGraph multi-agent systems — prompt injection firewall, Neo4j trust graphs, real-time anomaly detection & automated rollback. Built with FastAPI, React, Neo4j & Redis to secure autonomous AI agent swarms against adversarial attacks.

react python redis neo4j cybersecurity multi-agent-systems ai-safety anomaly-detection ai-agents trust-graph ai-security fastapi agentops prompt-injection llm-security langgraph llm-firewall self-healing-systems agent-orchestration generative-ai-security
  • Updated Jun 6, 2026
  • Python

api-evangelist / mindgard

Star 1

Mindgard — independent third-party profile of a public API surface, by API Evangelist. Mindgard is a UK-based offensive AI security company (London/Lancaster, spun out of Lancaster University) that provides an automated AI red-teaming and security testing platform for large language models, AI agents, and generative AI systems.

offensive-security ai-security mlops apis-json ai-governance prompt-injection llm-security ai-red-teaming generative-ai-security ai-discovery model-scanning jailbreak-testing ai-runtime-protection
  • Updated Sep 12, 2026

api-evangelist / concentric-ai

Star 0

Concentric AI — independent third-party profile of a public API surface, by API Evangelist. Concentric AI provides an AI-driven data security governance platform built on its proprietary Semantic Intelligence technology to autonomously discover, classify, monitor, and protect sensitive data across cloud and on-premises environments.

security company compliance data-security data-classification apis-json insider-risk generative-ai-security data-access-governance data-security-posture-management
  • Updated Sep 13, 2026

api-evangelist / hidden-layer

Star 0

HiddenLayer — independent third-party profile of a public API surface, by API Evangelist. HiddenLayer is an Austin, Texas-based AI security company founded in March 2022 by Chris Sestito (CEO), Tanner Burns (Chief Scientist), and Jim Ballard (CIO) — former Cylance researchers who encountered a real-world attack on production ML models.

security adversarial-machine-learning jailbreak-detection ai-security aisec apis-json ml-security prompt-injection aidr ai-guardrails shadow-ai ai-red-teaming mcp-security agentic-ai-security ai-supply-chain generative-ai-security ai-runtime-security model-scanning ai-detection-and-response ai-bill-of-materials
  • Updated Sep 12, 2026

Add this topic to your repo

To associate your repository with the generative-ai-security topic, visit your repo's landing page and select "manage topics."

Learn more