Dynamic Cyber Ranges

As LLM-driven agents advance in cybersecurity, Jeopardy CTF benchmarks are approaching saturation and cyber ranges, the natural next evaluation frontier, offer diminishing resistance under their current static design. We validate this observation by deploying an LLM-driven Advanced Persistent...

PT-2026-35512

A vulnerability was detected in JoeCastrom mcp-chat-studio up to 1.5.0. Affected by this issue is some unknown functionality of the file server/routes/llm.js of the component LLM Models API. Performing a manipulation of the argument req.query.base url results in server-side request forgery. Remot...

System-Aware Contextual Digital Twin for ICS Anomaly Diagnosis

Industrial Control Systems ICS integrate computing, physical processes, and communication to operate critical infrastructures such as power grids, water treatment plants, and oil and gas facilities. As ICS become increasingly targeted by cyberattacks, timely and reliable anomaly diagnosis is...

CVE-2026-7021

A weakness has been identified in SmythOS sre up to 0.0.15. This impacts an unknown function of the file packages/sdk/src/LLM/utils.ts of the component Connector Service. This manipulation of the argument baseURL causes information disclosure. It is possible to initiate the attack remotely. The...

Semantic Denial of Service in LLM-Controlled Robots

Safety-oriented instruction-following is supposed to keep LLM-controlled robots safe. We show it also creates an availability attack surface. By injecting short safety-plausible phrases 1-5 tokens into a robots audio channel, an adversary can trigger the models safety reasoning to halt or disrupt...

UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks

Emerging AR-LLM-based Social Engineering attack e.g., SEAR is at the edge of posing great threats to real-world social life. In such AR-LLM-SE attack, the attacker can leverage AR Augmented Reality glass to capture the image and vocal information of the target, using the LLM to identify the targe...

Automation-Exploit: A Multi-Agent LLM Framework for Adaptive Offensive Security with Digital Twin-Based Risk-Mitigated Exploitation

The offensive security landscape is highly fragmented: enterprise platforms avoid memory-corruption vulnerabilities due to Denial of Service DoS risks, Automatic Exploit Generation AEG systems suffer from semantic blindness, and Large Language Model LLM agents face safety alignment filters and...

Training a General Purpose Automated Red Teaming Model

Automated methods for red teaming LLMs are an important tool to identify LLM vulnerabilities that may not be covered in static benchmarks, allowing for more thorough probing. They can also adapt to each specific LLM to discover weaknesses unique to it. Most current automated red teaming methods a...

PT-2026-34780

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.3.28 Description An agentic consent bypass allows LLM agents to silently disable execution approval. Remote attackers can exploit this by using the config.patch parameter to bypass security controls and execute...

GHSA-J5W5-568X-RQ53 Evolver: Command Injection via `execSync` in `_extractLLM()` function allows Remote Code Execution

Summary A command injection vulnerability in the extractLLM function allows attackers to execute arbitrary shell commands on the server. The function constructs a curl command using string concatenation and passes it to execSync without proper sanitization, enabling remote code execution when the...

Text Steganography with Dynamic Codebook and Multimodal Large Language Model

With the popularity of the large language models LLMs, text steganography has achieved remarkable performance. However, existing methods still have some issues: 1 For the white-box paradigm, this steganography behavior is prone to exposure due to sharing the off-the-shelf language model between...

GHSA-3HJV-C53M-58JJ Flowise: CSV Agent Prompt Injection Remote Code Execution Vulnerability

Abstract Trend Micro's Zero Day Initiative has identified a vulnerability affecting FlowiseAI Flowise. Vulnerability Details - Version tested: 3.0.13 - Installer file: https://github.com/FlowiseAI/Flowise - Platform tested: Ubuntu 25.10 Analysis This vulnerability allows remote attackers to execu...

Cyber Defense Benchmark: Agentic Threat Hunting Evaluation for LLMs in SecOps

We introduce the Cyber Defense Benchmark, a benchmark for measuring how well large language model LLM agents perform the core SOC analyst task of threat hunting: given a database of raw Windows event logs with no guided questions or hints, identify the exact timestamps of malicious events. The...

SDLLMFuzz: Dynamic-Static LLM-Assisted Greybox Fuzzing for Structured Input Programs

Fuzzing has become a widely adopted technique for vulnerability discovery, yet it remains ineffective for structured-input programs due to strict syntactic constraints and limited semantic awareness. Traditional greybox fuzzers rely on mutation-based strategies and coarse-grained coverage feedbac...

Incomplete List of Disallowed Inputs

Overview flowise-components is a Flowiseai Components Affected versions of this package are vulnerable to Incomplete List of Disallowed Inputs in the run method of the AirtableAgents class, which evaluates LLM-generated Python scripts in a non-sandboxed environment. An attacker can execute...

HarmChip: Evaluating Hardware Security Centric LLM Safety Via Jailbreak Benchmarking

The integration of large language models LLMs into electronic design automation EDA workflows has introduced powerful capabilities for RTL generation, verification, and design optimization, but also raises critical security concerns. Malicious LLM outputs in this domain pose hardware-level threat...

Human Trust of AI Agents

Interesting research: "Humans expect rationality and cooperation from LLM opponents in strategic games." Abstract: As Large Language Models LLMs integrate into our social and economic interactions, we need to deepen our understanding of how humans respond to LLMs opponents in strategic settings. ...

SIR-Bench: Evaluating Investigation Depth in Security Incident Response Agents

We present SIR-Bench, a benchmark of 794 test cases for evaluating autonomous security incident response agents that distinguishes genuine forensic investigation from alert parroting. Derived from 129 anonymized incident patterns with expert-validated ground truth, SIR-Bench measures not only...

RRC Steganography

This is a proof of concept tool called Rotation Range-Coding RRC Steganography - an efficient and provably secure linguistic steganographic method that embeds secret messages into natural-language text generated by large language models. Included is the whitepaper discussing this tool called...

ADAM: A Systematic Data Extraction Attack on Agent Memory Via Adaptive Querying

Large Language Model LLM agents have achieved rapid adoption and demonstrated remarkable capabilities across a wide range of applications. To improve reasoning and task execution, modern LLM agents would incorporate memory modules or retrieval-augmented generation RAG mechanisms, enabling them to...