BrokenHill

!\ Broken Hill logo \https://assets.kitploit.com/production/public/readmes/44608/c14154675c6f33f5c3887887afcdb39351c82f269ee2772cf31847106a20a871.jpg Broken Hill Broken Hill is a productionized, ready-to-use automated attack tool that generates crafted prompts to bypass restrictions in large...

Stealing Reasoning Traces from Proprietary LLM APIs

Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage. Rather than storing these traces server-side, providers return them to the client as blocks of encrypted text, which the...

Agent against Agent: An Agentic System for Automatic Prompt Injection Red Teaming

Prompt injection poses significant security risks to LLM agents. Efficient and effective red-teaming is therefore critical, both for evaluating these risks and for collecting training data to improve defenses. Existing state-of-the-art prompt injection red-teaming methods primarily rely on...

DoubtProbe: Black-Box Jailbreak Defense Via Structural Verification and Semantic Auditing

As large language models LLMs are increasingly deployed in user-facing systems, black-box jailbreak defense has become an important practical problem. Existing defenses often rely on known-attack coverage, prompt-level semantic judgment, or local runtime control, yet these paths can become unstab...

Customization under Fire: Plugin Poisoning in Text-To-Image Ecosystem

The prosperity of text-to-image T2I models has fostered a vibrant share-and-play ecosystem centered on Low-Rank Adaptation LoRA plugins, which allow users to customize and share model capabilities with ease. This democratization, however, comes with a hidden but severe security risk. Malicious...

Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations

In this paper, we investigate whether refusal behavior can be predicted from LLM intermediate activations before decoding using linear probes trained on residual stream activations at each transformer block. We find that refusal is linearly decodable well before the final layer, indicating that...

CVE-2026-7020

CVE-2026-7020 affects Ollama up to version 0.20.2. The vulnerability lies in the digestToPath function (x/imagegen/transfer/transfer.go) where manipulating the digest enables path traversal. The attack can be performed remotely and is described as high complexity with a documented PoC/exploit. Co...

CVE-2026-7020 Ollama Tensor Model Transfer transfer.go digestToPath path traversal

A security flaw has been discovered in Ollama up to 0.20.2. This affects the function digestToPath of the file x/imagegen/transfer/transfer.go of the component Tensor Model Transfer Handler. The manipulation of the argument digest results in path traversal. The attack may be performed from remote...

Ollama path traversal vulnerability

Ollama is an open-source tool developed by Ollama that can be run locally, used for managing and customizing large language models. Ollama versions 0.20.2 and earlier had a path traversal vulnerability. This vulnerability stemmed from the operation of the digestToPath function in the Tensor Model...

PT-2026-35201

Name of the Vulnerable Software and Affected Versions Ollama versions prior to 0.20.2 Description A flaw in the Tensor Model Transfer Handler component allows remote attackers to perform path traversal. This occurs through the manipulation of the digest argument within the digestToPath function...

CVE-2026-7020: Improper Limitation of a Pathname to a Restricted Directory

A security flaw has been discovered in Ollama up to 0.20.2. This affects the function digestToPath of the file x/imagegen/transfer/transfer.go of the component Tensor Model Transfer Handler. The manipulation of the argument digest results in path traversal. The attack may be performed from remote...

Multi-Faceted Attack: Exposing Cross-Model Vulnerabilities in Defense-Equipped Vision-Language Models

The growing misuse of Vision-Language Models VLMs has led providers to deploy multiple safeguards, including alignment tuning, system prompts, and content moderation. However, the real-world robustness of these defenses against adversarial attacks remains underexplored. We introduce Multi-Faceted...

DAVSP: Safety Alignment for Large Vision-Language Models Via Deep Aligned Visual Safety Prompt

Large Vision-Language Models LVLMs have achieved impressive progress across various applications but remain vulnerable to malicious queries that exploit the visual modality. Existing alignment approaches typically fail to resist malicious queries while preserving utility on benign ones effectivel...

R1dacted: Investigating Local Censorship in DeepSeek'S R1 Language Model

DeepSeek recently released R1, a high-performing large language model LLM optimized for reasoning tasks. Despite its efficient training pipeline, R1 achieves competitive performance, even surpassing leading reasoning models like OpenAI's o1 on several benchmarks. However, emerging reports suggest...

Revealing Weaknesses in Text Watermarking through Self-Information Rewrite Attacks

Text watermarking aims to subtly embed statistical signals into text by controlling the Large Language Model LLM's sampling process, enabling watermark detectors to verify that the output was generated by the specified model. The robustness of these watermarking algorithms has become a key factor...