Comment and Control: Hijacking Agentic Workflows Via Context-Grounded Evolution

Automation platforms such as GitHub Actions and n8n are increasingly adopting so-called agentic workflows, which integrate Large Language Model LLM agents for tasks such as code review and data synchronization. While bringing convenience for developers, this integration exposes a new risk: An...

Can You Keep a Secret? Involuntary Information Leakage in Language Model Writing

Language models are deployed in settings that require compartmentalization: system prompts should not be disclosed, chain-of-thought reasoning is hidden from users, and sensitive data passes through shared contexts. We test whether models can keep prompted information out of their writing. We giv...

MARGIN: Margin-Aware Regularized Geometry for Imbalanced Vulnerability Detection

Software vulnerability detection is critical for ensuring software security and reliability. Despite recent advances in deep learning, real-world vulnerability datasets suffer from two severe challenges: frequency imbalance and difficulty imbalance. We reinterpret these challenges from an embeddi...

When Prompts Become Payloads: A Framework for Mitigating SQL Injection Attacks in Large Language Model-Driven Applications

Natural language interfaces to structured databases are becoming increasingly common, largely due to advances in large language models LLMs that enable users to query data using conversational input rather than formal query languages such as SQL. While this paradigm significantly improves usabili...

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...

PT-2026-39721

Name of the Vulnerable Software and Affected Versions jq versions prior to 1.8.2rc2 Description The ordinary module loader in this command-line JSON processor recurses without cycle detection when two valid modules include each other. Recommendations Update to a version later than 1.8.2rc1...

CVE-2026-8242

creationtimestamp| type| source ---|---|--- 2026-05-10 10:40:10+00:00| seen| https://bsky.app/profile/cve.skyfleet.blue/post/3mlil2ksay22q...

AgentShield: Deception-Based Compromise Detection for Tool-Using LLM Agents

Defenses against indirect prompt injection IPI in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks rather than detect the compromises that slip through. Second, they have only been evaluated in English, leaving users of low-resource languages such ...

erebus

EREBUS Web application security assessment framework. For...

centipede

centipede Self-replicating Linux worm framework with multi-la...

webhunter

🕷️ WebHunter — OWASP Top 10 AI Scanner !Pythonhttps://im...

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:...

AI Native Asset Intelligence

Modern security environments generate fragmented signals across cloud resources, identities, configurations, and third-party security tools. Although AI-native security assistants improve access to this data, they remain largely reactive: users must ask the right questions and interpret...

Enhancing Adversarial Robustness in Network Intrusion Detection: A Layer-Wise Adaptive Regularization Approach

The new wave of adversarial attacks that utilize gradient-related vulnerabilities in neural network-based classifiers makes Network Intrusion Detection Systems more open to such threats. Although state-of-the-art adversarial training methods have shown promising results in producing more robust...

CVE-2026-43435

A flaw was found in the Linux kernel's rustbinder component. The oneway spam detection logic in both TreeRange and ArrayRange was incorrectly implemented or missing, allowing large spamming transactions to go undetected. A local attacker could exploit this vulnerability to cause a Denial of Servi...

CVE-2026-41683

i18next-http-middleware is a middleware to be used with Node.js web frameworks like express or Fastify and also for Deno. Prior to version 3.9.3, i18next-http-middleware wrote user-controlled language values into the Content-Language response header after passing them through utils.escape, which ...

EUVD-2026-28741

In the Linux kernel, the following vulnerability has been resolved: rustbinder: fix oneway spam detection The spam detection logic in TreeRange was executed before the current request was inserted into the tree. So the new request was not being factored in the spam calculation. Fix this by moving...

UBUNTU-CVE-2026-43435

In the Linux kernel, the following vulnerability has been resolved: rustbinder: fix oneway spam detection The spam detection logic in TreeRange was executed before the current request was inserted into the tree. So the new request was not being factored in the spam calculation. Fix this by moving...

CVE-2026-43435 rust_binder: fix oneway spam detection

In the Linux kernel, the following vulnerability has been resolved: rustbinder: fix oneway spam detection The spam detection logic in TreeRange was executed before the current request was inserted into the tree. So the new request was not being factored in the spam calculation. Fix this by moving...

CVE-2026-43435 rust_binder: fix oneway spam detection

In the Linux kernel, the following vulnerability has been resolved: rustbinder: fix oneway spam detection The spam detection logic in TreeRange was executed before the current request was inserted into the tree. So the new request was not being factored in the spam calculation. Fix this by moving...