redteam-ai-benchmark

Red Team AI Benchmark Russian version: README.ru.md Red Team AI Benchmark is a CLI model-evaluation benchmark. It measures how LLMs understand and respond to red-team questions and security scenarios; it is not a tool for carrying out those activities. Version 2 uses a rubric-based dataset instea...

llm-prompt-injection-resources

llm-prompt-injection-resources A curated collection of resources for learning and researching LLM prompt injection attacks, defenses, and security. Donate Support the maintenance of this project with PayPal or by scanning the QR code below...

CVE-2026-33017

CVE-2026-33017 — Langflow Unauthenticated Remote Code Execution Author: dynamo2k1 Severity: Critical CVSSv3: 9.8 AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Overview CVE-2026-33017 is a critical unauthenticated Remote Code Execution vulnerability in Langflow, an open-source platform for visually building...

CVE-2026-108605

JeecgBoot versions through 3.9.5 are vulnerable to a missing authorization vulnerability in the AiOcrController updateById handler. This flaw allows any authenticated user to send PUT requests to the /airag/ocr/edit endpoint. An attacker can exploit this to overwrite LLM prompts in the shared air...

CVE-2026-108605 JeecgBoot through 3.9.5 Missing Authorization via /airag/ocr/edit Endpoint

JeecgBoot through 3.9.5 contains a missing authorization vulnerability in the AiOcrController updateById handler that allows any authenticated user to modify global OCR templates. Low-privileged attackers can send PUT requests to /airag/ocr/edit to overwrite LLM prompts in the shared airag:ocr...

ida-pro-mcp

IDA Pro MCP !IMPORTANT Consiglio invece di usare l'Official Hex-Rays IDA MCP Server! Consulta il post di annuncio sul blog per maggiori informazioni. Semplice MCP Server per consentire il vibe reversing in IDA Pro. https://github.com/user-attachments/assets/6ebeaa92-a9db-43fa-b756-eececce2aca0 I...

bring-your-own-key-cve-2026-73678-unauthenticated-rce-in-mindsdb-cowork

CVE-2026-73678 — Unauthenticated RCE in MindsDB Minds Platform / MindsHub Cowork PoC for CVE-2026-73678 CVSS 3.1 10.0 Critical , AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H. Full write-up: www.hunt-benito.com/blog/bring-your-own-key-cve-2026-73678-unauthenticated-rce-in-mindsdb-cowork/ The Cowork...

zairo

Measuring zairo zairo's unit tests check that it builds the right prompts and handles answers correctly. They can't tell you whether a model, given those prompts, finds a vulnerability a change introduced, or flags one that isn't there. That's what this directory is for: a set of labelled changes...

DeepGuard

DeepGuard 📖 Project Overview DeepGuard is an innovative secure code generation approach that enhances large language models' capability for secure code generation through multi-layer semantic aggregation techniques. This method effectively identifies and mitigates security vulnerabilities in code...

trustmebro

Bypass llm guardrails by confusing it with fabricated tool output. Results · Installation · Quick start · Rules · Architecture TrustMeBro intercepts command-line tools invoked by coding agents such as Codex, Claude Code, and pi. Rules decide whether to return fabricated output, modify the real...

BurpIA

BurpIA BurpIA turns Burp Suite into an AI-assisted web security testing environment. It analyzes real HTTP traffic with LLMs 12+ providers or local models, validates findings with autonomous CLI agents over Burp MCP, and keeps every result traceable — works on Burp Suite Community and Professiona...

FS-attack

Implementation of the paper "Rethinking Latency Denial-of-Service: Attack the LLM Serving Framework, Not the Model"...

Prompt-Injection-in-the-Wild

Prompt Injection in the Wild A tracker of publicly reported prompt-injection techniques from roughly the last two years, maintained by Rachel James cybershujin. Each technique is broken down into the three elements of a prompt injection: 1. Delivery method — how the injected instructions reach th...

SAFE

SAFE SAFE performs controlled, repository-aware security assessment of Semgrep and Trivy findings in research artifacts. It supports two independent classification tasks: direct binary prediction SECURITYRELEVANT or NONSECURITY and the detailed multiclass contextual taxonomy three labels — see...

bordair-detector

Bordair Detector A two-stage detector for prompt injection and jailbreak attempts in LLM inputs. A regex gate settles the easy majority of traffic without touching the model; anything ambiguous falls through to a quantised DeBERTa-v3 classifier running in ONNX. The same engine covers image,...

DAILA

DAILA The Decompiler Artificially Intelligent Language Assistant DAILA is a unified interface for AI systems to be used in decompilers. With DAILA, you can utilize various AI systems, like local and remote LLMs, all in the same scripting and GUI interfaces across many decompilers. DAILA was...

conductai

Conduct Governance for AI agents. Ship in 60 seconds. Built for engineering teams. Install in 10 minutes. Evidence for the CISO from day one. 60-second t...

CKA-Agent

ICML 2026 & ICLR 2026 AIWILD CKA-Agent: Bypassing LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search 🛡️ Defense towards CKA TurnGate is a response-aware defense mechanism designed to detect and mitigate hidden malicious intent in multi-turn dialogue systems. Defending...

resym

ReSym Artifact This repository provides artifacts for the paper "ReSym: Harnessing LLMs to Recover Variable and Data Structure Symbols from Stripped Binaries" CCS 2024. 🏆 ACM SIGSAC Distinguished Paper Award Winner Note : We are actively maintaining/updating our artifacts. Please make sure you ar...

standalone_tdo

TDO Standalone Extractor A powerful, standalone command-line tool for extracting Cyber Threat Intelligence CTI from documents using Large Language Models with advanced structured output capabilities. 🚀 Features Multi-format Document Support : PDF, DOCX, TXT, and Markdown files Advanced LLM...