delirium-ai-safety-benchmark

Delirium AI Safety Benchmark A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion ACE and related liminal attack vectors. Delirium is not an exploitation tool. It is a standardized benchmark designed to detect the precise moment when a language model's attention...

prompt_injection

Cross-Surface Prompt Injection Benchmark Benchmark for measuring where in a tool-using LLM agent's execution pipeline a prompt injection defense fires — and where it doesn't. Embeds unique canary tokens SECRET-A-F0-98 in injected payloads and tracks them at four pipeline stages: exposed → persist...

SEW

SEW: Style-Encoded Watermarking of LLM-Generated Code Paper Link 📖 📰 News 📢 NEW! The SEW paper is available on arXiv: arXiv:2609.39414. Sep 30, 2026 📢 The official SEW code has been released on GitHub. Sep 30, 2026 🔍 Motivation Feature| Token-level watermarks KGW, SWEET, Unigram, STONE, STA-1|...

FinRED-paper

FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming IEEE ICDM 2026 A red-team benchmark generation pipeline for safety evaluation in the financial domain. Supplementary Documentation Detailed materials referenced in the paper:...

IfritProxy

🔥 AI-Powered Threat Deception & Intelligence Platform Turn attackers into intelligence sources with adaptive honeypot responses 📦 Quick Start • ✨ Features • 🔄 How It Works • 📚 Docs • 🔌 API Brought to the community by 🎯 What is IFRIT? IFRIT is an intelligent reverse proxy that sits between the...

ai-code-review

🔍 codereview AI-powered code review in your terminal. One command. Instant feedback. Catches security vulnerabilities, bugs, and bad patterns before they hit production. Install · Quick Start · Usage · Providers · Contributing What It Does codereview sends your code to an LLM and returns a...

Scrapegraph-ai v2.3.1

🚀 Looking for an even faster and simpler way to scrape at scale only 5 lines of code? Check out our enhanced version at ScrapeGraphAI.com! 🚀 🕷️ ScrapeGraphAI: You Only Scrape Once English | 中文 | 日本語 | 한국어 | Русский | Türkçe | Deutsch | Español | français | Português | Italiano ScrapeGraphAI is a...

Xalgorix Autonomous AI Pentesting Agent 4.6.153

Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...

linux-kernel-codex-harness

Kernel Codex Harness 한국어 | English Strumento di Ricerca · Importazione Originale: 3 Aprile 2026 · Revisione Documentazione: 11 Luglio 2026 Filosofia Fondamentale — Segnale Esterno Lascia che osservazioni riproducibili al di fuori dell'inferenza del modello guidino l'attenzione; non scambiare mai ...

promptfoo v0.124.0

Promptfoo: LLM evals & red teaming promptfoo is a CLI and library for evaluating and red-teaming LLM-based apps. Stop using trial-and-error... start shipping secure, reliable agents Website · Getting Started · Red Teaming · Documentation · Discord Promptfoo is now part of OpenAI. Promptfoo remain...

Learning from Failures: A Failure-Driven Prompt Refinement for LLM-Based Vulnerability Analysis

Large Language Models have emerged as promising tools for software vulnerability analysis, but their effectiveness depends heavily on prompt design. Existing research primarily compares prompting strategies using aggregate performance metrics, providing limited insight into why models fail or how...

Xalgorix Autonomous AI Pentesting Agent 4.6.152

Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...

Newer and Bigger, but Safer? A Longitudinal Study of the Functionality-Security Gap in LLM-Generated Code

Large Language Models LLMs are widely used to generate code. Although their functional plausibility keeps improving, the generated code often contains security vulnerabilities. The functionality-security gap captures code that passes functional tests but fails security tests. A recent longitudina...

robin

Robin: strumento OSINT per il dark web basato sull'IA Robin è uno strumento basato sull'IA per condurre indagini OSINT sul dark web. Sfrutta gli LLM per perfezionare le query, filtrare i risultati di ricerca dai motori di ricerca del dark web e fornire un riepilogo dell'indagine. Installazione •...

RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents

Tool-using language-model agents are vulnerable to indirect prompt injection because they must act on untrusted external content. Existing training-time defenses can reduce attack success rates, but often at the cost of general capabilities. We show that training-based defenses induce substantial...

Towards a Unified Misuse Monitoring Benchmark

LLM agents increasingly act in multi-actor environments, exposing them to misuse from multiple sources: decomposition attacks, where a harmful request is split into innocuous sub-requests, and prompt injection attacks, where a compromised tool delivers a malicious instruction. Existing evaluation...

Safeguarding LLMs Via Model-Agnostic Latent Safety Signals from Dark Knowledge

LLMs have advanced rapidly, raising growing concerns about their safety. Recent work has proposed approaches to detect and defend against attacks including defenses at decoding stage that leverage models' hidden states. However, existing decoding-stage defenses suffer from two limitations. First,...

SkillPoison: Progressive Skill Poisoning Via Successful Experiences

Self-improving LLM agents increasingly distill successful experiences into persistent, reusable skills. Existing skill attack methods corrupt this learning pipeline by injecting malicious triggers, behaviors, or false facts into individual experiences or extracted skills. However, such attacks ar...

Xalgorix Autonomous AI Pentesting Agent 4.6.147

Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...

Compromise Is Not Consequence: Evaluating Task-Scoped Authorization in LLM Agents with Paired Replay

A tool-using model can follow a malicious instruction even when its credentials are valid. We study whether task-scoped authorization contains the resulting tool execution. Our paired-replay testbed samples a model request once and submits the same action, resource, and arguments to broad bearer,...