llm-censorship-steering

LLM Censorship Steering This repository contains code implementation for Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control by Hannah Cyberey and David Evans. We introduce a method that finds "steering vectors" from LLM internals for detecting and controlling the...

statecraftcyber

Statecraft Cyber Intelligence Threat intelligence platform in Portuguese built from scratch as a personal Blue Team project. It aggregates data from global open sources and turns it into technical briefings, classified news, enriched CVEs, and structured IOCs — all in PT-BR, continuously updated...

AI-Vulnerabilities-Playground

AIVP AI Vulnerabilities Playground AIVP is a hands-on AI security lab platform spanning 4 phases and 50+ labs currently 50+ scenarios across the codebase. It combines Ollama + Llama 3.1 , a FastAPI backend, and a React/Vite frontend to let practitioners safely practice offensive and defensive AI...

Llama-Stack-0.4.0rc3-local-CVE-2026-25211

Llama Stack pgvector Password Leak PoC CVE-2026-25211 Local Proof-of-Concept demonstrating plaintext database password exposure in initialization logs of llama-stack versions 0.4.0rc3. Overview In affected versions of llama-stack before 0.4.0rc3, when using the pgvector vector store provider, the...

D-Scan

When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse Official implementation of SIGIR 2026 paper When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse. D-SCAN is an analysis framework for detecting document poisoning attacks in RAG...

refusal-relocates

Project Page · Quick start · Usage · CLI · Results · Reproduce · FAQ · Citation News 2026-09-28 Code released, with the run records and scripts that rebuild the paper's tables. Overview A few dozen harmful examples can remove an aligned model's refusal of harmful requests. Prior work localizes...

Quotes llama <= 3.1.5 - SQL Injection

Quotes llama 3.1.5 and earlier contains a time-based blind SQL injection vulnerability caused by improper control of a SQL identifier. The selectsearch AJAX handler registered for guests via wpajaxnoprivselectsearch reads the attacker-controlled 'sc' parameter from $POST and substitutes it into t...

Exponentiated-Gradient-Descent-LLM-Attack

Change Readme File. This is a Project that explores the Exponentiated Gradient Descent optimizaiton method to produce adversarial suffix to attack algined Large Language Models. The method is shown to be effective on Llama-2 chat model with 7 Billion parameters. To run pgd script on a number of...

one-multiply-too-many-cve-2026-70638-llama-cpp-android-jni-integer-overflow

CVE-2026-70638 - llama.cpp LLaMA-Android JNI Integer Overflow Companion PoC for the Hunt-Benito article "One Multiply Too Many: CVE-2026-70638 — Integer Overflow in llama.cpp's Android JNI Heap Allocation" →...

LlamaStack-RCE-Deterministic-Supply-Chain-Exploitation-Hardening-Framework-CVE-2024-50050-

= doi.org/10.5281/zenodo.18278567 = orcid.org/0009-0007-7728-256X 💀 LlamaStack-RCE: CVE-2024-50050 Supply Chain Exploitation Framework UNRESTRICTED CLASSIFIED MATERIAL - FOR AUTHORIZED RED TEAMING ONLY 1. Executive Summary Deterministic Analysis LlamaStack-RCE is a high-fidelity simulation and...

llama_facts

Llama Facts This project was originally created for the Rochester Institute of Technology RIT Women in Cybersecurity WIYCS 2022 CTF competition. It is vulnerable to Server-Side Template Injection SSTI, defined in the disputed CVE CVE-2019-8341. Challenge Description Description: A Computer Scienc...

llama-factory-webui-rce-cve-2026-58116-trust-remote-code-model-path-injection

CVE-2026-58116 — LLaMA-Factory WebUI RCE via trustremotecode Proof of concept for CVE-2026-58116 CVSS 9.8 Critical: remote code execution in LLaMA-Factory = v0.9.5. The LLaMA-Factory WebUI hardcodes trustremotecode=True when loading a model src/llamafactory/webui/chatter.py:139 and...

CVE-2026-112080

A vulnerability was found in LlamaChinese Llama-Chinese up to 6fa0fffb0dd82fe3cfaa1449ee54a5806d26ae9b. The impacted element is the function getclassfromdynamicmodule of the file examples/chatgradionomerge.py of the component Adapter Config. The manipulation of the argument basemodelnameorpath...

EUVD-2026-104068

A vulnerability was found in LlamaChinese Llama-Chinese up to 6fa0fffb0dd82fe3cfaa1449ee54a5806d26ae9b. The impacted element is the function getclassfromdynamicmodule of the file examples/chatgradionomerge.py of the component Adapter Config. The manipulation of the argument basemodelnameorpath...

PT-2026-117224

A vulnerability was found in LlamaChinese Llama-Chinese up to 6fa0fffb0dd82fe3cfaa1449ee54a5806d26ae9b. The impacted element is the function get class from dynamic module of the file examples/chat gradio no merge.py of the component Adapter Config. The manipulation of the argument base model name...

CVE-2026-112080: Improper Control of Generation of Code

A vulnerability was found in LlamaChinese Llama-Chinese up to 6fa0fffb0dd82fe3cfaa1449ee54a5806d26ae9b. The impacted element is the function getclassfromdynamicmodule of the file examples/chatgradionomerge.py of the component Adapter Config. The manipulation of the argument basemodelnameorpath...

Evidence-Grounded LLM-Assisted Android Mobile Forensic Reporting

Large language models can assist forensic report drafting, but fluent output does not ensure evidentiary reliability. This study presents an evidence-grounded framework for evaluating LLM-assisted Android forensic reports at the atomic-claim level. Gemini, Llama, and Qwen each generated reports f...

Linux Distros Unpatched Vulnerability : CVE-2026-107183

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - llama.cpp before b11393 contains a use-after-free and double free vulnerability in commonchatpegmapper::map that allows unauthenticated remote attackers to...

DEBIAN-CVE-2026-107183

llama.cpp before b11393 contains a use-after-free and double free vulnerability in commonchatpegmapper::map that allows unauthenticated remote attackers to corrupt heap memory via a dangling currenttool pointer. Attackers can submit a chatparser in a POST /completion request emitting a tool-id...

CVE-2026-107183

llama.cpp before b11393 contains a use-after-free and double free vulnerability in commonchatpegmapper::map that allows unauthenticated remote attackers to corrupt heap memory via a dangling currenttool pointer. Attackers can submit a chatparser in a POST /completion request emitting a tool-id...