SpliTEE: Improving LLM Inference on Trusted Hardware with Differentially Private GPU Outsourcing

User prompts provided to large language models LLMs may contain sensitive or private information that can be misused by remotely deployed models, such as through inadvertent memorization during retraining. One way to protect user prompts is to execute the LLM inside a trusted execution environmen...

Automating Attack Graph Construction for Agentic Pentesting. Towards Neuro-Symbolic Vulnerability Hunting

Logic attack graphs grounded in scanner output provide explicit and auditable attack path reasoning LLM-based agents lack. Integrating symbolic frameworks such as MulVAL to contemporary security workflows or agentic pipelines, however, requires translating scanner evidence to initial facts, and...

Evaluating the NIST Bugs Framework against CWE As a Successor for Automated Vulnerability Classification

Vulnerability classification based on root cause weaknesses is essential for numerous cybersecurity activities, where the Common Weakness Enumeration CWE serves as a public repository of such flaws. However, its overlapping entries create a non-orthogonal structure. The result is the same...

The Model Proposes, the Code Disposes: A Pre-Registered Ablation of a Verifier-And-Acceptance Stage in an LLM-Orchestrated Offensive-Security Agent

We evaluate whether a verifier-and-acceptance stage - a model verifier whose verdicts are enforced by deterministic code - changes what an LLM-driven offensive-security agent reports. We report a 15-run exploratory pilot, a pre-registered 20-run confirmatory ablation, and a pre-registered 2 x 2...

Adversarial Testing of Automated Program Repair Agents for Security Vulnerabilities

Software agents with Large Language Models LLMs are designed for Automated Program Repair APR tasks, raising the possibility that, in the near future, APR agents will fix bugs automatically without much human intervention. Can we trust an APR agent to produce both functionally correct and secure...

RuleAutoPilot: Synthesizing Deployable Suricata Rules from Network Traffic

Rule-based Intrusion Detection Systems IDS such as Suricata are central to network security, yet crafting effective detection rules demands deep expert knowledge and cannot keep pace with emerging threats. Existing LLM-based approaches can reduce analyst effort, but they either rely on curated...

MAL-2026-16143 Malicious code in chroma-client (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector f0c415e6cd4e653006225dd54672dd79ef076166a2015fa33bbf8f10b789af55 The distribution installs a.pth file that Python auto-executes at interpreter startup on every process using the environment. The.pth file's executab...

Malicious code in chroma-client (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector f0c415e6cd4e653006225dd54672dd79ef076166a2015fa33bbf8f10b789af55 The distribution installs a.pth file that Python auto-executes at interpreter startup on every process using the environment. The.pth file's executab...

JGD

⚡ JGD JavaGadgetDigger — Solving the Last Mile of Deseria...

osmedeus v5.1.1

Osmedeus Osmedeus - A Modern Orchestration Engine for Security What is Osmedeus? Osmedeus is a security focused declarative orchestration engine that simplifies complex workflow automation into auditable YAML definitions, complete with encrypted data handling, secure credential management, and...

CVE-2026-90534 Flowise before 3.1.4 Cross-Workspace Credential IDOR via node-load-method

Flowise is a low-code platform for building LLM applications. In versions up to and including 3.1.3, the POST /api/v1/node-load-method/:name endpoint is mounted without any route-level permission check and invokes component loadMethods with an attacker-controlled nodeName, loadMethod, inputs, and...

EUVD-2026-76852

Flowise is a low-code platform for building LLM applications. In versions up to and including 3.1.3, the POST /api/v1/node-load-method/:name endpoint is mounted without any route-level permission check and invokes component loadMethods with an attacker-controlled nodeName, loadMethod, inputs, and...

CVE-2026-90534

Flowise , a low-code platform for building LLM applications, is affected by a Cross-Workspace Credential IDOR in the POST /api/v1/node-load-method/:name endpoint through version 3.1.3 . The endpoint lacks route-level permission checks and resolves credentials by raw Credential.id via getCredentia...

Trustworthy Agentic AI: A Comprehensive Cybersecurity and Systems Survey on Threat Landscapes, Defense Architectures, and Open Challenges

The transition from passive foundation models to autonomous, goal-directed agentic AI systems has introduced unprecedented capabilities by coupling recursive cognitive reasoning loops, persistent memory architectures, live tool execution planes, and multi-agent collaboration topologies. However,...

AGENTQ: Quantization-Conditioned Backdoor Attacks on LLM Agents

Quantization is one of the default deployment paths for open-weight LLM agents, but it is not behavior-preserving: an adversary can release a full-precision checkpoint that passes audits yet misbehaves once quantized, termed as quantization-conditioned attack QCA. Prior QCA work targets free-text...

CVE-2026-71416

Headroom compresses data before the data reaches a large language model. Prior to version 0.35.0, the Headroom WebSocket server does not validate the Origin header of incoming client WebSocket requests before forwarding the request to the upstream server, allowing malicious WebSocket clients to...

CVE-2026-71416 Headroom vulnerable to Cross-Site WebSocket Hijacking (CSWSH)

Headroom compresses data before the data reaches a large language model. Prior to version 0.35.0, the Headroom WebSocket server does not validate the Origin header of incoming client WebSocket requests before forwarding the request to the upstream server, allowing malicious WebSocket clients to...

CVE-2026-71416 Headroom vulnerable to Cross-Site WebSocket Hijacking (CSWSH)

Headroom compresses data before the data reaches a large language model. Prior to version 0.35.0, the Headroom WebSocket server does not validate the Origin header of incoming client WebSocket requests before forwarding the request to the upstream server, allowing malicious WebSocket clients to...

CVE-2026-71416 Headroom vulnerable to Cross-Site WebSocket Hijacking (CSWSH)

Headroom compresses data before the data reaches a large language model. Prior to version 0.35.0, the Headroom WebSocket server does not validate the Origin header of incoming client WebSocket requests before forwarding the request to the upstream server, allowing malicious WebSocket clients to...

CVE-2026-71416

Headroom is a WebSocket proxy that compresses data before it reaches a large language model. Prior to version 0.35.0 , its WebSocket server fails to validate the Origin header of incoming client WebSocket requests before forwarding them to the upstream server. This allows a Cross-Site WebSocket H...