The Sub-10-Minute Cloud Takeover: How Exposed IAM Keys, Misconfiguration and AI Are Rewriting the Rules of Cloud Breaches

Key Takeaways Two real-world cloud attacks reached meaningful impact in less than ten minutes despite pursuing entirely different objectives. Both attackers treated the environment as a connected system, using existing permissions and relationships to expand their reach. Reconnaissance increasing...

DeepFaith: Evidence-Grounded LLMs for Faithful Incident Reporting in Multi-Stage APT Defense

Advanced Persistent Threats APTs are difficult to detect and interpret due to their multi-stage and stealthy nature. While recent autonomous defense systems leverage provenance graphs and learning-based models for detection and mitigation, their outputs remain largely machine-oriented and difficu...

When LLM Defenses Backfire: Characterizing Safety, Performance, and Cost Trade-Offs

Jailbreak defenses are essential for protecting large language models LLMs, but they can also introduce secondary costs that weaken model utility. We present a systematic study of these defense trade-offs along three dimensions: performance impact, over-refusal on benign inputs, and inference cos...

Just Testing, Move Along: Evasion of LLM-Based System Log Interpretation by Prompt Injection

Large Language Models LLMs are increasingly integrated into Security Operations Center SOC workflows, where they support analysts in tasks such as the interpretation of system logs. However, the ability of LLMs to directly process untrusted textual input also introduces new attack surfaces. In...

TYPO: Instruction-Dense Visual Jailbreaks against Commercial Closed-Source Image-Generation Models

Recent commercial image-generation models can generate high-quality images with readable text e.g., posters, infographics, and manuals, attracting considerable attention. Yet we first show that this same capability also introduces a previously unreported safety vulnerability: these systems may...

Xerox Printers Remote Command Execution (CVE-2021-28671)

Xerox Phaser 6510 before 64.65.51 and 64.59.11 Bridge, WorkCentre 6515 before 65.65.51 and 65.59.11 Bridge, VersaLink B400 before 37.65.51 and 37.59.01 Bridge, B405 before 38.65.51 and 38.59.01 Bridge, B600/B610 before 32.65.51 and 32.59.01 Bridge, B605/B615 before 33.65.51 and 33.59.01 Bridge,...

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors Via Adversarial Code Comments

Large language models are increasingly deployed for security-sensitive tasks such as vulnerability detection and code review. Their reliance on natural-language context embedded in source code exposes a previously underexplored attack surface: adversarial comments that can influence a detector's...

DarkPrompt

DarkPrompt !CIhttps://github.com/jason-allen-oneal/DarkPr...

The OpenAI Models That Hacked Hugging Face Were ‘Active on the Internet’ for Days

Plus: Russian hackers are trying to steal US nuclear scientists’ emails, the State Department bans known scammers from entering the United States, and more...

CVE-2026-64362 HID: lg-g15: cancel pending work on remove to fix a use-after-free

In the Linux kernel, the following vulnerability has been resolved: HID: lg-g15: cancel pending work on remove to fix a use-after-free lgg15data is allocated with devm and holds a work item. The report handlers schedule that work straight from device input. lgg15event and lgg15v2event do it on th...

False Prophets: On the Security of World Models in Agentic Systems

Large language models now power autonomous agents capable of complex, multi-step tasks in different environments. Accurate and reliable execution of these tasks requires the agent to predict the results of its actions. Recent research proposes to enhance predictive capabilities via specially...

A Structured Cyber Threat Intelligence Dataset Using STIX 2.1 Entities and MITRE ATT&CK Mappings

Cyber threat intelligence CTI reports are typically written in unstructured formats, which complicates the extraction and analysis of important entities and adversarial behaviors. Although existing CTI research provides extraction tools, knowledge-graph frameworks, and MITRE ATT&CK mapped dataset...

Poster: Rethinking Security in LLM Code Generation through Real-World Risk Scenarios

Large Language Models LLMs are widely used for code generation, yet their security behavior in realistic development workflows remains underexplored. Existing benchmarks often rely on explicitly specified security requirements, failing to capture real-world scenarios where prompts are frequently...

GHSA-2625-RW7M-5Q5X Hubuum client library (Rust): Sensitive data may be exposed through default diagnostics

Summary hubuumclient diagnostics can expose sensitive request, response, import/export, task, delivery, or server-provided data when applications format or log errors and public models. Affected behavior Native reqwest::Error values retain the full request URL. Converting those errors into...

Missing Authorization

Overview open-webui is an Open WebUI Affected versions of this package are vulnerable to Missing Authorization in the generatechatcompletion process. An attacker can gain unauthorized access to restricted underlying models by submitting crafted requests to task endpoints that leverage readable...

Open WebUI: Arena task endpoints can bypass underlying model access controls

Summary An authenticated non-admin user with read access to an arena wrapper model can reach a restricted underlying model through task endpoints such as /api/v1/tasks/moa/completions. The normal chat route resolves arena models before the final chat dispatch and therefore re-checks the selected...

EUVD-2026-42639

Open WebUI: Arena task endpoints can bypass underlying model access controls...

Open WebUI: Model meta.knowledge read-only file access can be upgraded to file write/delete

Summary Current main and v0.9.6 still allow an authenticated user to turn read-only access to another user's file into write/delete access by attaching that file ID to an attacker-controlled workspace model. This is an incomplete-fix variant of GHSA-vjqm-6gcc-62cr. The current fix adds...

GHSA-GH7P-78X6-JW6M Open WebUI: /api/v1/channels/{id}/members exposes full user model including sensitive credentials

Summary The channel members endpoint serializes and returns full user models for channel participants, including settings objects. A normal user in a DM can retrieve admin-only sensitive configuration such as webhook URLs and tool server key material settings.ui.toolServers.key, which is not...

Open WebUI: /api/v1/channels/{id}/members exposes full user model including sensitive credentials

Summary The channel members endpoint serializes and returns full user models for channel participants, including settings objects. A normal user in a DM can retrieve admin-only sensitive configuration such as webhook URLs and tool server key material settings.ui.toolServers.key, which is not...