
openclaw-defender
Multi-layer security framework for AI agent ecosystems. Provides pre-installation skill auditing, file integrity monitoring, runtime protection, and…

Multi-layer security framework for AI agent ecosystems. Provides pre-installation skill auditing, file integrity monitoring, runtime protection, and…

AI-powered CLI tool that reviews code for security vulnerabilities, bugs, and anti-patterns using LLMs. Supports local and cloud providers, git…

PowerShell-based detection and remediation toolkit for CVE-2025-32711 (EchoLeak), a critical zero-click AI command injection vulnerability in…

SecureML - Securing and Watermarking AL models

Proof-of-concept demonstrating remote code execution via request-side prompt injection in OpenClaw Agent Platform, exploiting lack of integrity…

Reproducible vulnerable and fixed GitHub Actions fixtures for agentic workflow injection (CVE-2026-44246), with measured detector coverage and…

Fingerprint OpenAI-compatible LLMs from tokenizer and behavior signals.

Research code implementing backdoor attack and defense methods for LLMs, including IBSD, SLIP, BeDKD, and BadApex algorithms.

Pre-auth RCE scanner for Langflow < 1.8.0 — Route Injection + Vertex Injection → Code Execution (CVSS 9.8)

Security patches for unpatched llama.cpp vulnerabilities (CVE-2026-43626 through CVE-2026-43632) — Cyera Research

CVE-2026-73678 — MindsDB Minds Platform unauthenticated RCE via scratchpad exec (CVSS 10.0). Verified end-to-end with real LLM

Proof-of-concept exploit for CVE-2026-33017, an unauthenticated RCE in Langflow's build_public_tmp endpoint, injecting a malicious custom component…

The code in "DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization"

FastGPT Python sandbox escape chain audit tool (CVE-2026-32128 related, v4.14.8 inspect chain)

PoC reproducer for CVE-2026-49042 (Apache Camel camel-langchain4j-tools): a prompt-injected LLM's tool-call arguments become unfiltered Exchange…

A terminal-based AWS Security Scanner with 102+ security checks across VPC, IAM, S3, CloudTrail, containers (ECS/EKS), and AI attack detection.…

A Red Team vs. Blue Team Adversarial AI Simulation.

Research implementation of a poisoning attack against retrieval-augmented language models using camouflaged documents to evade filtering defenses and…