A Red-Team Study of Anthropic Fable 5 and Opus 4.8 Models

We evaluate the adversarial robustness of two frontier large language models LLMs developed by Anthropic, Fable 5 and Opus 4.8, against four families of automated jailbreak attack across 7 826 harmful intents spanning a ten-category harm taxonomy. Using the HackAgent red-teaming framework, hundre...

CVE-2026-12206: Improper Neutralization of Special Elements used in an SQL Command

A vulnerability was identified in Grit42 Grit up to 0.11.0. This issue affects the function Grit::Assays::DataTableEntity of the file modules/assays/backend/app/models/grit/assays/datatableentity.rb. The manipulation leads to sql injection. The attack is possible to be carried out remotely. The...

AttackonCTF: Defending Hardware Security Competition Benchmarks in the Age of LLMs

Hardware security competitions such as HackTheSilicon serve as benchmarking platforms for evaluating vulnerability detection methods and for training humans and AI. However, our study reveals that LLMs threaten their validity. Instead of genuine security reasoning, detectors exploit a diff-style...

OffSploit

OffSploit: Autonomous Exploit Adaptation & C2 Framework !Py...

U.S. Orders Anthropic to Suspend Fable 5 and Mythos 5 Access for Foreign Nationals

Anthropic said on Friday it will "abruptly disable" its most advanced artificial intelligence AI models, Claude Fable 5 and Mythos 5 , for all users after the U.S. government ordered it to suspend access to the models for foreign nationals, whether inside or outside the U.S., citing national...

Data-Centric Benchmarking of Exploit Generation in LLMs: Understanding the Impact of Fine-Tuning

We study the task of CVE-conditioned exploit generation, where a model drafts proof-of-concept PoC exploits given software vulnerability context. We adopt a data-centric approach, constructing a high-quality dataset via multi-stage preprocessing and introducing a scalable evaluation framework wit...

Evaluating LLMs for Obfuscation Detection and Classification in Android Apps

Android applications apps developers increasingly rely on code obfuscation techniques to hinder reverse engineering and protect intellectual property. However, obfuscation also reduces the effectiveness of static analysis and vulnerability detection tools, creating challenges for Android security...

Investigating Metamorphic Fuzz Oracle Enhancement Via Large Language Models

Fuzz drivers are essential components of greybox fuzzing, as they encapsulate target interfaces, define test spaces, and largely determine fuzzing effectiveness. Existing fuzz drivers typically rely on crash-based oracles for security testing, overlooking library functionality and limiting bug...

Criminal AI-as-a-Service in 2026: How the Underground Market Is Operationalizing Cybercrime

Introduction The underground market for criminally oriented generative AI has moved beyond the early hype surrounding 'malicious chatbots.' The gradual integration of AI as a productivity layer within cybercrime operations has become the dominant story, indicating that while the potential for ful...

PT-2026-50833

Name of the Vulnerable Software and Affected Versions Hitachi Virtual Storage Platform E990, E1090, E1090H versions prior to DKCMAIN Ver.93-07-21-80/00-05, CHBiSCSI Ver.88-01-02-04 Hitachi Virtual Storage Platform E390, E590, E790, E390H, E590H, E790H versions prior to DKCMAIN...

SEVRA-BENCH: Social Engineering of Vulnerabilities in Review Agents

Large language model LLM reviewers are increasingly used in pull-request PR workflows, where their approvals help decide which code is merged into a repository. This raises a question that benchmarks for static vulnerability detection or code generation do not address: can an automated reviewer...

CVE-2026-46645 SQLAdmin: Authorization Bypass on `ajax_lookup`

SQLAdmin is a flexible Admin interface for SQLAlchemy models. Prior to version 0.25.1, the ajaxlookup endpoint in application.py bypasses the isaccessible access control check that all other endpoints enforce. If a developer restricts model access by overriding isaccessible, an authenticated user...

CVE-2026-9212

Insufficient authentication and input validation in the listed NETGEAR models allow users connected to the local network to execute commands impacting the product's confidentiality or change certain configurations...

CVE-2026-0420

An improper implementation of TLS certificate validation vulnerability found in NETGEAR's ReadyCloud client app which could allow an attacker to perform attacker-in-the-middle MiTM style attacks impacting the product's confidentiality. This vulnerability affects the listed NETGEAR models...

CVE-2026-0414

Insufficient input validation vulnerability in the listed NETGEAR models allows authenticated administrators connected to the local network to make unauthorized modification of router software and functionality...

CVE-2025-40808

A vulnerability has been identified in SIPROTEC 5 6MD84 CP300 All versions, SIPROTEC 5 6MD85 CP200 All versions, SIPROTEC 5 6MD85 CP300 All versions, SIPROTEC 5 6MD86 CP200 All versions, SIPROTEC 5 6MD86 CP300 All versions, SIPROTEC 5 6MD89 CP300 All versions, SIPROTEC 5 6MU85 CP300 All versions,...

Ollama System Data Compromise Check Missing

The vulnerability of the Ollama system for running and managing large language models is related to the loading of code without checking its integrity. Exploiting this vulnerability allows a remote attacker to execute arbitrary code...

PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections

Large Language Models LLMs are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security risks such as indirect prompt injection attacks through untrusted external sources. Existing defenses mainly focus on blocking malicious content at...

Can Open-Source LLM Agents Replace Static Application Security Testing Tools? an Empirical Assessment

This paper explores the value of agentic AI tools for cybersecurity purposes. We evaluate the efficacy of a general-purpose GenAI Large Language Model- GenAI- based agent when powered by three different Ollama-hosted general-purpose open source models. We assess each agent's performance using...

odd-cli (>=0.1.1, <=0.1.10), odd-collector-sdk (>=0.2.4, <=0.3.56) +4 more potentially affected by CVE-2026-46373 via sqlfluff (3.0.3)

sqlfluff PYPI version 3.0.3 is affected by a known vulnerability. The following packages have a transitive dependency on sqlfluff and may be impacted: - odd-cli =0.1.1, =0.2.4, =0.2.3, =2.0.32, =2.0.46 - sqlfluff-templater-dbt 3.0.3 - sqllineage 1.5.2 Source cves: CVE-2026-46373 Source advisory:...