HARP: Hierarchical Adaptive Ranking with Preference-Adaptive Fusion for Query-Based CVE Prioritization

Vulnerability prioritization is inherently preference dependent, since the same CVE can receive different remediation priority under different operational preference scenarios. Existing scoring systems and ranking methods typically assume a fixed criterion. In practice, organizations already...

PT-2026-80735

Summary export space and import space tools in @contentful/mcp-tools accept LLM-controlled host and proxy parameters that are spread directly into the options object passed to contentful-export / contentful-import. These libraries pass the merged options — including the attacker-controlled host —...

Improving LLM-Based SSH Honeypots through Prompting and Fine-Tuning

LLM-based SSH honeypots often use closed cloud LLMs because they give strong shell realism, but cloud models create deployment problems. These include no stable versioning, provider-side changes, attacker-driven cost, and model decommissioning. Local open-weight models avoid these problems, but...

CVE-2026-75857 CodeWhale before 0.8.64 Privilege Escalation via exec_shell_interact

CodeWhale versions = 0.8.41 and 0.8.64 contain a vulnerability in the execshellinteract alias execinteract tool, whose approvalrequirement returns ApprovalRequirement::Auto. This overrides the default Required approval for code-executing tools, so LLM-controlled stdin is written into an...

skyvern v1.0.50

🐉 Automate Browser-based workflows using LLMs and Computer Vision 🐉 Skyvern automates browser-based workflows using LLMs and computer vision. It provides a Playwright-compatible SDK that adds AI functionality on top of playwright, as well as a no-code workflow builder to help both technical and...

LLMs and Contextual Integrity

I have been thinking a lot about AI and integrity. Part of that is contextual integrity. I recently found two papers on the topic. "CIMemories: A Compositional Benchmark for Contextual Integrity of Persistent Memory in LLMs": Abstract: Large Language Models LLMs increasingly use persistent memory...

CVE-2026-75857: Improper Privilege Management

CodeWhale versions = 0.8.41 and 0.8.64 contain a vulnerability in the execshellinteract alias execinteract tool, whose approvalrequirement returns ApprovalRequirement::Auto. This overrides the default Required approval for code-executing tools, so LLM-controlled stdin is written into an...

Incident-Data Robustness Analysis of the OWASP Top 10 for LLM Applications (2026): How a Community-Expert Ranking Holds up against a Large-Scale LLM Incident Corpus

The OWASP Top 10 for LLM Applications ranks the risks that a community of security practitioners judges most important. We ask a narrower question: checked against the record of real incidents, does that expert ranking agree with the data? We assembled a large-scale corpus of LLM-security inciden...

MobileWorldSafety: Benchmarking GUI Agent Safety against Environmental Injection Attacks in Android Apps

LLM-powered GUI agents that autonomously operate smartphones are rapidly transitioning from research prototypes to early real-world deployment. However, because these agents routinely process untrusted environmental content, they are highly vulnerable to environmental injection attacks, which...

Benchmarking Automated Security Patch Backporting: How Far Are We?

Automated security patch backporting is critical for mitigating N-day vulnerabilities. Recent tools report success rates above 80% on their respective datasets. However, these evaluations are often confined to homogeneous environments, such as one repository or specific project versions...

Fair ASR: Re-Evaluating Black-Box Jailbreaks under Shared Target-Call Budgets

Reliable jailbreak evaluation is essential for assessing LLM safety, but most existing studies rely solely on attack success rate ASR without accounting for its dependence on attack budgets, resulting in unfair comparisons across methods. Existing compute-aware evaluations reduce heterogeneous...

qwen3.8-9b-cyber-exploit-agent-uncensored

Qwen3.8-9B Cyber Exploit Agent — UNCENSORED Identical fine-tu...

CVE-2026-75110 MemOS Authentication Bypass via Unset INTERNAL_SERVICE_SECRET

MemOS is a memory operating system for LLMs and AI agents. In deployments where authentication is enabled AUTHENABLED=true but the undocumented, defaultless INTERNALSERVICESECRET environment variable is unset, the isinternalrequest check in src/memos/api/middleware/auth.py fails open:...

augustus v0.14.20

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...

LLMs for Zero-Shot Threat Detection Via Structured Risk Indicators

We propose a two-stage large language model LLM framework for zero-shot detection of insider threats and advanced persistent threats APTs from heterogeneous security logs. The framework models user activity as chronological timelines and incorporates retrieval-augmented generation RAG to provide...

Beyond the Hype: Evaluating LLM Integration and Practical Limitations in Security Operation Centers

Large Language Models LLMs are increasingly being explored within Security Operation Centers SOCs to support text-heavy analytical work such as alert contextualization, incident summarization, and drafting investigative artifacts. Despite this interest, practitioners describe critical operational...

MindsDB Minds Platform Cowork Unauthenticated Remote Code Execution

MindsDB Minds Platform Cowork contains an unauthenticated remote code execution vulnerability in the Cowork server API where unauthenticated settings modification can be combined with the Anton agent scratchpad functionality to execute arbitrary Python code without sandboxing. This proof of conce...

Topological Attribution Distance (TAD): Revealing Segment-Level RAG Influence on LLM Output Geometry for Incident Log Analysis

Large Language Models LLMs are increasingly being deployed in cybersecurity operations to assist cybersecurity analysts with rapid decision-making against emerging threats. However, there is a main criteria that must be met when using LLMs in cybersecurity, that is, trust in the generated outputs...

Securing AI-Generated Code: A Just-In-Time Vulnerability Detection and Remediation Pipeline

AI-assisted development tools generate vulnerable code at significant rates, yet few automated mechanisms exist to detect, enrich, fix, and verify security issues at development velocity, particularly ones that ground remediation in real-world threat context. This paper presents an automated...

The OWASP LLM Top 10 Was the Warm-Up: What Comes Next

This is Post 3 of a four-part series: Post 1: Agentic AI Security: The Chatbot Era Is Over Post 2: Generative AI Security: Why AI Needs a New Kind of Security Post 4: OWASP LLM Top 10 2026: Every Move Points the Same Direction When the OWASP Top 10 for LLM Applications arrived, it did the industr...