9Router has an Authentication Bypass in Public LLM API via Spoofable X-9r-Real-Ip Header

9router determines whether an incoming request originates from localhost by trusting the X-9r-Real-Ip HTTP request header. This header is intended to be produced and sanitized exclusively by the bundled custom-server.js layer from the TCP socket address. In deployment modes where requests reach...

APT-Hunter V4.0

APT-Hunter Threat hunting for Windows event logs, built with a purple-team mindset. APT-Hunter is a threat hunting tool for Windows event logs. It uses pre-defined detection rules and log statistics to surface APT activity hidden in large volumes of events, cutting the time needed to uncover...

Attack Success Rate Is Not a Number: On Measurement Validity in Agentic AI Security Evaluation

Attack success rate ASR is the headline metric in nearly every published evaluation of attacks on, and defenses for, LLM agents. We argue that ASR as currently used is not a single quantity but a family of metrics parameterized by six design choices that papers seldom specify and never hold...

Reasoning Topology Matters: A Controlled Study of LLM-Based Cybersecurity Analysis

Large Language Models LLMs are increasingly used in cybersecurity, where accurate analysis often requires multi-step and context-dependent reasoning over complex and heterogeneous data. However, existing prompting approaches typically focus on eliciting reasoning without explicitly considering ho...

Indirect Tipping: A Social Attack Surface in AI Agent Populations

As generative AI agents are deployed at scale, safety will depend not only on technical safeguards and individual model design, but also on collective equilibria that determine how agent populations process information, prioritize actions, and respond to uncertainty. Yet the same equilibria that...

OPBackdoor: Opportunistic Backdoors Via Alibi-Aligned Reasoning

When a backdoor trigger activates the target response regardless of the triggered prompt context, the backdoor objective reveals itself. Challenging this trigger-sufficient formulation across the LLM backdoor literature, we introduce Opportunistic Backdoors OPBackdoor, in which the backdoor...

Decepticon v1.1.44

Decepticon — Autonomous Red Team Agent "Another AI hacker? Let us guess — it runs nmap and writes a report." Commercial product demo ☁️ Don't want to self-host? Decepticon is live in the cloud. Skip the Docker setup — run autonomous red-team engagements right from your browser. Open-source CLI dem...

Xalgorix Autonomous AI Pentesting Agent 4.6.83

Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...

xalgorix v4.6.78

Xalgorix — Open-source AI pentester that proves vulnerabilities Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported — so you get proof, not a pile of maybes to triage...

claude-security-audit

Claude Security Audit A complete security auditor for Clau...

CASCADE against Jailbreaks: Combination across Stages with Controlled Attack-Defense Evaluation

Defenses against jailbreak attacks on Large Language Models LLMs operate at different pipeline stages, such as input modification or output guard, but it remains unclear which defenses to deploy at each stage and how to combine them. Prior empirical studies, fragmented by inconsistent...

Guardrails v0.24.1

NVIDIA NeMo Guardrails Library LATEST RELEASE / DEVELOPMENT VERSION : The develop branch tracks the latest top of tree development. The latest released version is 0.24.1. ✨✨✨ 📌 The official NeMo Guardrails library documentation is available atdocs.nvidia.com/nemo/guardrails. ✨✨✨ NVIDIA NeMo...

Malicious code in marketing-mcp (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 87216e00fe68e2de8b140f1f9ffc2db5a8e814f38030e2eb6120c9ae9e7ca3ff The package exposes an MCP tool sendpath that reads a caller-specified local file and POSTs its contents to a hardcoded...

MAL-2026-16250 Malicious code in marketing-mcp (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 87216e00fe68e2de8b140f1f9ffc2db5a8e814f38030e2eb6120c9ae9e7ca3ff The package exposes an MCP tool sendpath that reads a caller-specified local file and POSTs its contents to a hardcoded...

WeaveMark

WeaveMark Implementación de referencia de Robust and Scalable Multi-bit LLM Watermarking via Coded Payload Spreading. WeaveMark incrusta un mensaje de k bits en texto generado por LLM manteniendo la distribución de tokens imparcial. Combina la dispersión de carga codificada κ bits de palabra de...

ALIBI: Adversarial Legitimacy Injection in Binary Input against LLM Malware Analyzers

Large language models are being integrated into malware triage workflows as reasoning components that summarize static evidence and produce analyst-facing verdicts. This paper shows that the same reasoning capability introduces a new attack surface. We present ALIBI, a semantic cover story attack...

SoK: Trading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading Schemes

Autonomous large language model LLM agents are moving rapidly into high-stakes domains, yet existing agentic-AI security studies remain largely domain-agnostic and overlook the distinctive, high-consequence attack surface such settings create. We examine this gap through financial trading agents,...

Allocation of Resources Without Limits or Throttling

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling through the inputaudio processing path in /v1/chat/completions. An attacker can cause excessive...

augustus v0.14.30

Augustus - LLM vulnerability scanner for prompt injection, jailbreak, and adversarial attack testing Augustus - LLM Vulnerability Scanner Test large language models against 210+ adversarial attacks covering prompt injection, jailbreaks, encoding exploits, and data extraction. Augustus is a Go-bas...

CVE-2026-69147

A flaw was found in vLLM, an inference and serving engine for large language models. An attacker can exploit this by submitting specially crafted video requests that force the use of the PyNvVideoCodec GPU decoder. This bypasses the engine's static GPU memory reservation, allowing the attacker to...