Decoding Guardrails: XAI-Guided Perturbation Analysis of Prompt Injection Detection

Large language models LLMs are increasingly deployed in production systems, raising concerns about their exposure to adversarial manipulation through prompt injection and jailbreak attacks. Classifier-based guardrails, such as Prompt Guard 2, are widely used as a first line of defense against suc...

CVE-2026-90712

A vulnerability was identified in Gitlawb openclaude up to 0.30.0. Impacted is the function waitForCallback of the file src/services/api/xaiOAuthCallback.ts of the component xAI OAuth Callback Handler. The manipulation of the argument Error leads to denial of service. Remote exploitation of the...

CVE-2026-90712

A denial of service vulnerability was identified in Gitlawb openclaude up to version 0.30.0 , affecting the waitForCallback function in the file src/services/api/xaiOAuthCallback.ts within the xAI OAuth Callback Handler component. The root cause is manipulation of the Error argument, which can le...

CVE-2026-90712 Gitlawb openclaude xAI OAuth Callback xaiOAuthCallback.ts waitForCallback denial of service

A vulnerability was identified in Gitlawb openclaude up to 0.30.0. Impacted is the function waitForCallback of the file src/services/api/xaiOAuthCallback.ts of the component xAI OAuth Callback Handler. The manipulation of the argument Error leads to denial of service. Remote exploitation of the...

CVE-2026-90712 Gitlawb openclaude xAI OAuth Callback xaiOAuthCallback.ts waitForCallback denial of service

A vulnerability was identified in Gitlawb openclaude up to 0.30.0. Impacted is the function waitForCallback of the file src/services/api/xaiOAuthCallback.ts of the component xAI OAuth Callback Handler. The manipulation of the argument Error leads to denial of service. Remote exploitation of the...

CVE-2026-90712 Gitlawb openclaude xAI OAuth Callback xaiOAuthCallback.ts waitForCallback denial of service

A vulnerability was identified in Gitlawb openclaude up to 0.30.0. Impacted is the function waitForCallback of the file src/services/api/xaiOAuthCallback.ts of the component xAI OAuth Callback Handler. The manipulation of the argument Error leads to denial of service. Remote exploitation of the...

PT-2026-91173

A vulnerability was identified in Gitlawb openclaude up to 0.30.0. Impacted is the function waitForCallback of the file src/services/api/xaiOAuthCallback.ts of the component xAI OAuth Callback Handler. The manipulation of the argument Error leads to denial of service. Remote exploitation of the...

CVE-2026-90712: Improper Resource Shutdown or Release

A vulnerability was identified in Gitlawb openclaude up to 0.30.0. Impacted is the function waitForCallback of the file src/services/api/xaiOAuthCallback.ts of the component xAI OAuth Callback Handler. The manipulation of the argument Error leads to denial of service. Remote exploitation of the...

Clearview AI Is Testing an AI Tool That Would Let Cops Unearth Your Life Online

InquiryIQ, a previously unreported prototype, tested a model from xAI, maker of Grok, to surface associates, social accounts, and other information about people identified through Clearview...

New Cryptographic Context Injection Attack Could Let Web Pages Steal Grok Chat Data

Adversa AI has disclosed an attack technique that it says can cause xAI's Grok chatbot to send a user's name, approximate location, subscription tier, and the prompts from the ongoing conversation to an attacker-controlled server after the user asks it to summarize an ordinary web page. The AI...

A Comparison of Malware Image Transformations Using Grad-CAM and Hybrid Learning Models

Recent studies have shown that binary-to-image representations can enable effective machine learning-based results for malware detection and classification. However, performance can vary significantly, depending on the technique used to convert binaries to images. Furthermore, the explainability...

Dueling Deep Q-Learning for Intrusion Detection

Intrusion detection systems IDS and automated systems for detecting and reporting cyber threats, are commonly handled via supervised machine learning methods. Though effective, these models struggle to effectively adapt to new attack types. This study proposes a novel approach by employing a...

Conversational Versus Dashboard Explainable AI for UAV Intrusion Detection: An Empirical Study of Operator Trust and Reliance

Machine learning-based Intrusion Detection Systems IDS have demonstrated superior performance in securing Unmanned Aerial Vehicle UAV networks. However, the 'black-box' nature of these models, combined with the high dimensionality of multimodal cyber-physical data, poses significant...

PT-2026-67754

Name of the Vulnerable Software and Affected Versions hermes-agent versions prior to 0.16.1 Description A flaw in the xAI Image Generation Provider component allows for remote server-side request forgery SSRF, a condition where an attacker can induce the server to make requests to an unintended...

CVE-2026-18774: Server-Side Request Forgery (SSRF)

A flaw has been found in NousResearch hermes-agent up to 0.16.0. This affects the function saveurlimage of the file agent/imagegenprovider.py of the component xAI Image Generation Provider. This manipulation causes server-side request forgery. The attack may be initiated remotely. The exploit has...

DOGE Denizen Marko Elez Leaked API Key for xAI

Marko Elez , a 25-year-old employee at Elon Musk's Department of Government Efficiency DOGE, has been granted access to sensitive databases at the U.S. Social Security Administration, the Treasury and Justice departments, and the Department of Homeland Security. So it should fill all Americans wi...

CVE-2024-4484

The The Plus Addons for Elementor – Elementor Addons, Page Templates, Widgets, Mega Menu, WooCommerce plugin for WordPress is vulnerable to Stored Cross-Site Scripting via the ‘xaiusername’ parameter in versions up to, and including, 5.5.2 due to insufficient input sanitization and output escapin...

Developer Leaks API Key for Private Tesla, SpaceX LLMs

In AI, as with so many advancing technologies, security often lags innovation. The xAI incident, during which a sensitive API key remained exposed for nearly two months, is a stark reminder of this disconnect. Such oversights not only jeopardize proprietary technologies but also highlight systemi...

xAI Dev Leaks API Key for Private SpaceX, Tesla LLMs

An employee at Elon Musk's artificial intelligence company xAI leaked a private key on GitHub that for the past two months could have allowed anyone to query private xAI large language models LLMs which appear to have been custom made for working with internal data from Musk's companies, includin...

Meta is using your public Facebook and Instagram posts to train its AI

Post anything publicly on Facebook and Instagram? Meta has likely been using those posts to train its AI, according to the company's top policy executive. In an interview with Reuters, Meta President of Global Affairs Nick Clegg said the company used the public posts to train the LLM large langua...