strix-advanced

⚡ Strix-Advanced AI-Powered Security Testing Platform An...

PT-2026-39742

CVE-2026-20352 iOS 26.3-Research A Public Open-Source research framework with .py and .sh files created for analyzing iOS 26.3 security mechanisms. This project is designed to be advanced through the collective in... https://t.co/5O6AR6f6H7...

A Systematic Security Testing Approach for InterUSS-Based Environments

Unmanned Traffic Management UTM federated ecosystems, such as InterUSS, enable secure coordination among UAS Service Suppliers USSs. However, they bring up some security challenges at the infrastructure level that haven't been fully explored. This paper presents a security testing approach for...

Comment and Control: Hijacking Agentic Workflows Via Context-Grounded Evolution

Automation platforms such as GitHub Actions and n8n are increasingly adopting so-called agentic workflows, which integrate Large Language Model LLM agents for tasks such as code review and data synchronization. While bringing convenience for developers, this integration exposes a new risk: An...

Can a Single Message Paralyze the AI Infrastructure? the Rise of AbO-DDoS Attacks through Targeted Mobius Injection

Large Language Model LLM agents have emerged as key intermediaries, orchestrating complex interactions between human users and a wide range of digital services and LLM infrastructures. While prior research has extensively examined the security of LLMs and agents in isolation, the systemic risk of...

Guaranteed Jailbreaking Defense Via Disrupt-And-Rectify Smoothing

This paper proposes a guaranteed defense method for large language models LLMs to safeguard against jailbreaking attacks. Drawing inspiration from the denoised-smoothing approach in the adversarial defense domain, we propose a novel smoothing-based defense method, termed Disrupt-and-Rectify...

Agentic Fuzzing: Opportunities and Challenges

Fuzzers and static analyzers find many bugs but struggle with logic bugs in mature codebases. Triggering such a bug often requires multi-step reasoning that produces no distinctive execution feedback, and variants can appear across implementations too different for a single pattern to match. Rece...

MAL-2026-3509 Malicious code in pp-react-v5 (npm)

pp-react-v5 is a dependency confusion package published at the inflated version 10.0.0 to win npm resolution over any internally-hosted package of the same name. The package contains only a package.json with no functional source code. On installation the preinstall script executes a wget command...

MAL-2026-3420 Malicious code in noon-contracts (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 5e2a4c1ac3896b7769b47ab6659bf7b0d49f229963c910d0c9b9be11c5291c12 The package noon-contracts was found to contain malicious code. Source: ossf-package-analysis...

MAL-2026-3412 Malicious code in post-purchase-bundler (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 3a33aa69ef958573a786f3db208d8ee335829e14009d1fdafecbc842ed493b8b The package post-purchase-bundler was found to contain malicious code. Source: ossf-package-analysis...

pocxgen-agent

PoCXGen Agent An LLM-orchestrated multi-agent pipeline for au...

Malicious code in @miurba/alcazaba (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 36c814274998998c89db63740c3d1032c8da3d6f6f9e44e100328c83e4ea29a0 The package @miurba/alcazaba was found to contain malicious code. Source: ossf-package-analysis...

MAL-2026-3410 Malicious code in @miurba/alcazaba (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 36c814274998998c89db63740c3d1032c8da3d6f6f9e44e100328c83e4ea29a0 The package @miurba/alcazaba was found to contain malicious code. Source: ossf-package-analysis...

Position: AI Security Policy Should Target Systems, Not Models

We present swarm-attack, an open-source adversarial testing framework in which multiple lightweight LLM agents coordinate through shared memory, parallel exploration, and evolutionary optimization. Together, our results demonstrate that both safety bypass of frontier models and software...

Malicious code in apple-mycelium-fix (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector e69a2534c8bb0842243808b87451a399a8fc121ee56e755a33627f21035f8e33 The package apple-mycelium-fix was found to contain malicious code. Source: ghsa-malware...

webhunter

🕷️ WebHunter — OWASP Top 10 AI Scanner !Pythonhttps://im...

MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks

Multi-turn jailbreaks exploit the ability of large language models to accumulate and act on conversational context. Instead of stating a harmful request directly, an attacker can gradually steer the conversation toward an unsafe answer. Recent methods demonstrate this risk, but they are usually...

PT-2026-39402

Name of the Vulnerable Software and Affected Versions Yii Framework versions prior to 2.0.55 Description Internal variables in the View::renderPhpFile and ErrorHandler::renderFile functions are not isolated, which can lead to parameter collisions that allow the overriding of included file paths...

claude-skills-exploit

Security Research Skills Reusable skills for vulnerability an...

Friday Squid Blogging: Giant Squid Live in the Waters of Western Australia

Evidence of them has been found by analyzing DNA in the seawater. As usual, you can also use this squid post to talk about the security stories in the news that I haven't covered. Blog moderation policy...