Windows/x86 (XP SP3) (English) calc.exe Shellcode

15 bytes small Windows/x86 XP SP3 English calc.exe shellcode...

Context-Aware Spear Phishing: Generative AI-Enabled Attacks against Individuals Via Public Social Media Data

We demonstrate how publicly available social-media data and generative AI GenAI can be misused to automate and scale highly personalized, context-aware spear-phishing campaigns. With minimal attacker effort, a small amount of public activity per target is sufficient for GenAI models to extract...

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...

Janus: Compiler-Based Defense against Transient Execution Attacks Using ARM Hardware Primitives

We present Janus, a compiler-based security framework that mitigates transient execution attacks like Spectre and control-flow hijacking on ARM64 platforms. Janus integrates speculative execution and control flow dependencies with PA modifiers, using PA and BTI microarchitectural features to...

Re-Triggering Safeguards within LLMs for Jailbreak Detection

This paper proposes a jailbreaking prompt detection method for large language models LLMs to defend against jailbreak attacks. Although recent LLMs are equipped with built-in safeguards, it remains possible to craft jailbreaking prompts that bypass them. We argue that such jailbreaking prompts ar...

AI-Accelerated Brute Force Cryptanalysis

Modern cryptography is hinged on "not learning from mistakes": trying numerous wrong keys, should not help one identify the right key. Indeed, it worked -- until recently when the surprising power of AI to see pattern in apparent randomness has turned the 'wrong plaintexts' generated by the 'wron...

PT-2026-41171

Name of the Vulnerable Software and Affected Versions Open WebUI versions prior to 0.9.3 Description Open WebUI renders user-uploaded Office files, such as Excel and DOCX, as HTML using the @html directive without applying DOMPurify sanitization. This lack of sanitization allows for Stored...

GHSA-H4FW-6R7F-W494 Webauthn has a User Verification Downgrade via Default-Open ClientOverridePolicy

Summary In version 5.3.0 of the Symfony bundle, Webauthn\Bundle\Policy\ClientOverridePolicy defaulted to allowing all client overrides, including userVerification. A client could send "userVerification": "discouraged" in the assertion or attestation options request to override a server-configured...

Webauthn has a User Verification Downgrade via Default-Open ClientOverridePolicy

Summary In version 5.3.0 of the Symfony bundle, Webauthn\Bundle\Policy\ClientOverridePolicy defaulted to allowing all client overrides, including userVerification. A client could send "userVerification": "discouraged" in the assertion or attestation options request to override a server-configured...

When prompts become shells: RCE vulnerabilities in AI agent frameworks

In this article 1. A representative case study: Semantic Kernel 2. CVE-2026-26030: In-Memory Vector Store 3. CVE-2026-25592: Arbitrary file write through SessionsPythonPlugin 4. The vulnerability 5. Attack chain overview 6. Defending the agentic edge 7. Not bugs, but developed by design 8. CTF...

Gotenberg has a Server-Side Request Forgery (SSRF) Issue

Summary The SSRF hardening shipped in v8.31.0 only covers outbound URLs that Gotenberg's Go code handles — Chromium asset fetches, webhook delivery, and download-from. The LibreOffice conversion endpoint /forms/libreoffice/convert passes uploaded documents directly to LibreOffice without inspecti...

groovestrike

GrooveStrike Autonomous Penetration Testing Framework...

SecureMCP: A Policy-Enforced LLM Data Access Framework for AIoT Systems Via Model Context Protocol

The deployment of Large Language Model LLM-generated SQL queries in Artificial Intelligence of Things AIoT systems introduces critical security risks, as prompt injection attacks can manipulate LLMs into producing unauthorized queries that expose sensitive data or execute destructive operations...

PT-2026-37460

Name of the Vulnerable Software and Affected Versions Linux kernel affected versions not specified Description A null pointer dereference can occur when filemap release folio is invoked on a folio belonging to a mapping with AS RELEASE ALWAYS set but without a defined release folio operation. In...

Gray-Box Poisoning of Continuous Malware Ingestion Pipelines

Modern malware detection pipelines rely on continuous data ingestion and machine learning to counter the high volume of novel threats. This work investigates a realistic gray-box poisoning threat model targeting these pipelines. Using the secmlmalware framework, we generate problem-space...

The Adversarial Discount - AI, Signal Correlation, and the Cybersecurity Arms Race

We study a contest-theoretic model of adversarial investment in which an attacker and a defender allocate resources to AI-augmented capabilities across multiple attack surfaces. The attacker's investment operates through two channels: it amplifies offensive potency unconditionally and erodes...

ARGUS: Defending LLM Agents against Context-Aware Prompt Injection

The rise of Large Language Model LLM agents, augmented with tool use, skills, and external knowledge, has introduced new security risks. Among them, prompt injection attacks, where adversaries embed malicious instructions into the agent workflow, have emerged as the primary threat. However,...

PIIGuard: Mitigating PII Harvesting under Adversarial Sanitization

Browsing-enabled LLM assistants can fetch webpages and answer contact-seeking queries, creating a practical channel for scraping contact-style personally identifiable information PII from public pages. Many prior defenses are deployed at the model, service, or agent layer rather than at the webpa...

Autonomous LLM Agent Worms: Cross-Platform Propagation, Automated Discovery and Temporal Re-Entry Defense

Autonomous LLM agents operate as long-running processes with persistent workspaces, memory files, scheduled task state, and messaging integrations. These features create a new propagation risk: attacker-influenced content can be written into persistent agent state, re-enter the LLM decision conte...

Stable Agentic Control: Tool-Mediated LLM Architecture for Autonomous Cyber Defense

Agentic systems involved in high-stake decision-making under adversarial pressure need formal guarantees not offered by existing approaches. Motivated by the operational needs of security operations centers SOCs that must configure endpoint detection and response EDR policies under adversarial...