RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attacks

Reasoning-capable large language models can be induced to spend their generation budget on injected decoy tasks rather than answering the user's question, causing denial of service when no final answer is produced and denial of wallet when excess output tokens are billed. Input-side safety...

BAIT: Boundary-Guided Disclosure Escalation Via Self-Conditioned Reasoning

In this work, we propose BAIT Boundary-Aware Iterative Trap, a three-step jailbreak framework that approaches malicious goals through internal disclosure. BAIT first asks the model to identify the protection boundary, then requires it to refine that boundary, and finally requests a detailed...

CyberMaskQA: A Privacy-Aware Benchmark for Evaluating Large Language Models in Cybersecurity Question Answering

Large language models LLMs are increasingly applied to cybersecurity question answering QA for critical tasks such as incident response and vulnerability analysis. However, real-world operational contexts, including system logs and network configurations, inherently contain sensitive identifiers,...

sec-recon-agent

sec-recon-agent Type-safe security triage built on Pydantic A...

Three Heads Are Better Than One: A Multi-Perspective Reasoning Framework for Enhanced Vulnerability Detection

Automated vulnerability detection is crucial for enhancing software security by identifying potential flaws that attackers could exploit, thereby reducing the reliance on labor-intensive manual code audits. Recent advancements have shifted towards leveraging large language models LLMs for...

Rethinking Side-Channel Analysis: Automated Discovery and Analysis of Side-Channel Leakage with LLM-Assisted Agents

Side-channel attacks exploit unintended information leakage from system behavior and continue to pose serious privacy risks in modern platforms. Despite extensive prior work, side-channel analysis remains largely manual and fragmented, typically assuming predefined target events and a fixed set o...

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...

Adversarial SQL Injection Generation with LLM-Based Architectures

SQL injection SQLi attacks are still one of the serious attacks ranked in the Open Worldwide Application Security Project OWASP Top 10 threats. Today, with advances in Artificial Intelligence AI, especially in Large Language Models LLMs, an opportunity has been created for automating adversarial...

Oracle Poisoning: Corrupting Knowledge Graphs to Weaponise AI Agent Reasoning

We define Oracle Poisoning, an attack class in which an adversary corrupts a structured knowledge graph that AI agents query at runtime via tool-use protocols, causing incorrect conclusions through correct reasoning. Unlike prompt injection, Oracle Poisoning manipulates the data agents reason ove...

Smart Contract Security beyond Detection

Smart contract security has progressed from vulnerability detection toward a broader research agenda that includes semantic reasoning, automated repair, adversarial robustness, and real-time exploit detection. This paper develops a capstone-oriented research narrative around four directions:...

Securing the Dark Matter: A Semantic-Enhanced Neuro-Symbolic Framework for Supply Chain Analysis of Opaque Industrial Software

Automated vulnerability detection in critical-infrastructure software confronts a fundamental barrier: industrial software is routinely deployed as stripped, symbol-free binaries that deprive conventional Software Composition Analysis of the source-level transparency it requires. Existing binary...

GoAT-X: A Graph of Auditing Thoughts for Securing Token Transactions in Cross-Chain Contracts

Cross-chain bridges, the critical infrastructure of the multi-chain ecosystem, have become a primary target for attackers, resulting in over $2.8 billion in losses due to subtle implementation flaws. Existing defenses, such as bytecode-level static analysis, are ill-equipped to handle the semanti...

DarkWin-NGASR

🌌 DARKWIN — Next-Gen Automated Security Research Develope...

Metasploit Wrap-Up 04/25/2026

Check Method Visibility Metasploit has supported check methods for many years now. It’s not always desirable to jump straight into exploiting a vulnerability but instead to determine if the target is vulnerable. Metasploit tries to be very conservative with classifying a target as “vulnerable”...

CVE-2026-41344

OpenClaw before 2026.3.28 contains a privilege escalation vulnerability in the chat.send endpoint that allows write-scoped gateway callers to persist admin-only verboseLevel session overrides. Attackers can exploit the /verbose parameter to bypass access controls and expose sensitive reasoning or...

CVE-2026-41344 OpenClaw < 2026.3.28 - Privilege Escalation via chat.send /verbose Parameter

OpenClaw before 2026.3.28 contains a privilege escalation vulnerability in the chat.send endpoint that allows write-scoped gateway callers to persist admin-only verboseLevel session overrides. Attackers can exploit the /verbose parameter to bypass access controls and expose sensitive reasoning or...

CVE-2026-41344

OpenClaw before 2026.3.28 contains a privilege escalation vulnerability in the chat.send endpoint that allows write-scoped gateway callers to persist admin-only verboseLevel session overrides. Attackers can exploit the /verbose parameter to bypass access controls and expose sensitive reasoning or...

vlnr

vlnr: Autonomous Vulnerability Discovery Pipeline !Python 3...

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.3.28 contained security vulnerabilities. These vulnerabilities stemmed from a permission escalation vulnerability in the chat.send endpoint, allowing gatekeepers with write...

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. ...