#1LLM security, prompt injection, model extraction, adversarial AI, and AI red teaming tools.
Kitploit recommended

Provenance-aware Linux kernel vulnerability research harness used in the investigation of CVE-2026-53075

Safety cannot be a prompt instruction. TBP provides an external execution-layer boundary for autonomous agents, enforcing hard F/I/W invariants via…

AI-driven endpoint governance platform that monitors software usage, applies deterministic policy-based risk classification, and generates structured…

Benchmark code and interactive results for autonomous network-attack detection by tool-using LLM agents investigating raw PCAPs.

Runtime security gateway for AI agents: cryptographically attests tool calls, enforces policies, sandboxes execution, and logs tamper-evident audit…

Evidence-driven Linux kernel vulnerability research harness used in the investigation of CVE-2026-31720

Security control plane for LLM agents: allowlists, owner kill switch, PIN sessions, rate limits, prompt-injection detection, and output scrubbing to…

Structured security knowledge base with production-inspired cases: vulnerability analysis, exploit explanation, remediation, and DevSecOps for…

Aurea is an open-source, AI-powered platform that secures infrastructure-as-code (IaC) across Terraform, Kubernetes, Docker, and Ansible. It…

AI-powered security co-pilot that catches vulnerabilities as you code. Real-time security scanning, educational explanations, and auto fixes for…

Live recon and posture auditing for AI agent infrastructure: scans MCP configs, session logs, and APIs for secrets, poisoned catalogs, and CoT leaks.

Two-stage prompt-injection and jailbreak detector: regex gates plus a quantised DeBERTa-v3 ONNX classifier, with image, document, and audio support.…

SafeForge is an open-source mobile app hub built on GitLab that enables developers to build, upload, and share applications in a secure, AI-verified…

A static + runtime security scanner for MCP (Model Context Protocol) servers

Reproduces CVE-2026-44246, a prompt injection vulnerability in nnU-Net's GitHub Actions triage agent, demonstrating how issue content is inlined into…

Local white-box gradient attacks for open-weight LLMs: GCG/PEZ suffix search, layer saliency, weight snapshots, and rank-1 suffix-to-delta fitting…

Securekit is a protocol-agnostic security kernel that enforces zero-trust, sandboxed execution for AI tool use. It sits between any LLM or agent…

Proof-of-concept demonstrating prompt injection in Langchain's GraphCypherQAChain leading to SQL injection in Neo4j databases. Includes Docker-based…