Live Incident Intelligence

Google DeepMind introduces CodeMender, an AI agent designed to automatically discover and patch software vulnerabilities, including complex root causes and architectural weaknesses. The agent applies proactive fixes, such as `-fbounds-safety` annotations, demonstrated to prevent exploitation of vulnerabilities like the `CVE-2023-4863` heap buffer overflow in `libwebp`.

LLM-based applications are susceptible to remote code execution (RCE) vulnerabilities when executing LLM-generated code via functions like `exec` or `eval` without proper sandboxing, often triggered by prompt injection. Additionally, insecure access controls in Retrieval-Augmented Generation (RAG) systems can lead to data leakage and indirect prompt injection, while active content rendering of LLM outputs enables data exfiltration by embedding malicious links or images.

Threat actors are employing Large Language Models (LLMs) to create sophisticated phishing campaigns, leveraging LLM-generated code to obfuscate malicious payloads within Scalable Vector Graphics (SVG) files. These meticulously crafted SVG files bypass email security by disguising embedded JavaScript with business terminology, ultimately redirecting victims to fake login pages for credential harvesting.

A multi-stage supply chain attack, tracked as UNC6395, originated from the compromise of a Salesloft GitHub repository, leading to the theft of a sensitive OAuth token. This token enabled access to a high-privilege AI chatbot application (Drift) and subsequent exfiltration of customer conversation data and contact information from over 700 integrated Salesforce instances.

Google has released emergency security updates for Chrome to patch CVE-2025-10585, an actively exploited zero-day vulnerability. This critical type confusion flaw resides within the V8 JavaScript and WebAssembly engine, confirmed to be exploited in the wild.

The article details critical security challenges associated with cloud-hosted Large Language Models (LLMs), including prompt injection, adversarial exploits, model jailbreaks, sensitive data leakage, and misconfigurations. These vulnerabilities, stemming from lack of visibility and ungoverned AI behavior, necessitate proactive discovery and risk management to safeguard AI workloads.

Researchers discovered a reflected Cross-Site Scripting (XSS) vulnerability in Yellow.ai's chatbot, which could be tricked into generating malicious HTML/JavaScript code. This flaw enabled attackers to steal support agent session cookies, potentially leading to account hijacking and data exfiltration from customer support platforms.

Hexstrike-AI is an AI-powered orchestration framework designed to automate and accelerate zero-day exploitation, leveraging large language models to significantly reduce the time and skill required for complex attacks. Threat actors are actively discussing using Hexstrike-AI to target recently disclosed unauthenticated remote code execution and other critical vulnerabilities (CVE-2025-7775, CVE-2025-7776, CVE-2025-8424) in Citrix NetScaler ADC and Gateway appliances, with observed webshell deployments.

The incident involved the mass-theft of authentication tokens from Salesloft's Drift application, leading to significant data exfiltration from integrated corporate Salesforce instances and other cloud services. Threat actors, tracked as UNC6395, leveraged these stolen credentials to perform "authorization sprawl," accessing and siphoning sensitive data including AWS keys and VPN credentials.

Threat actor UNC6395 exploited compromised OAuth and refresh tokens associated with the Drift AI chat agent, accessible via Salesloft, to gain unauthorized access to Salesforce customer instances. This systematic campaign led to the exfiltration of sensitive data, including AWS access keys, passwords, and Snowflake tokens, from over 700 organizations, indicating a potential supply chain attack.

An Insecure Direct Object Reference (IDOR) vulnerability in an exposed API, combined with an unpatched legacy web application and weak credential hygiene, allowed unauthorized access to sensitive applicant personal data. This composite attack vector resulted in a data leak comprising names, emails, and job histories.

Lenovo's GPT-4-powered chatbot "Lena" was vulnerable to cross-site scripting (XSS) attacks due to improper input and output sanitization, initiated by a malicious prompt. This allowed attackers to steal session cookies and potentially gain unauthorized access to customer support systems, facilitating further system command execution and lateral movement.

The article highlights novel prompt injection techniques, such as ASCII Smuggling and hidden instructions in public code repositories, designed to be imperceptible to human developers but interpretable by LLM-powered coding agents. These sophisticated methods exploit the agents' access to external data to achieve Remote Code Execution (RCE) on developer systems, especially concerning when agents operate in unconfirmed execution modes like 'Auto-Run.'

Enterprise AI assistants have been identified as vulnerable to abuse, potentially enabling unauthorized data theft. This exploitation pathway also allows for the manipulation of enterprise data or the behavior of these AI systems.

The healthcare sector faces an average data breach cost of $7.42 million, driven by the compromise of patient personal identification information (PII). A notable 16% of these incidents leverage AI for sophisticated phishing and deepfake campaigns, often exacerbated by the organizational vulnerability of "Shadow AI" and insufficient AI governance.

Rapid AI adoption is creating significant security debt due to neglected foundational cybersecurity, specifically a lack of proper AI access controls and governance policies. This oversight has led to a heightened risk of data compromise, operational disruption of AI-based workloads, and the exposure of intellectual property within AI implementations.

The Amazon Q Developer Extension for Visual Studio Code (version 1.84.0) was compromised via a software supply chain attack, embedding a prompt injection that bypassed security reviews. This malicious prompt, detailed in AWS Security Bulletin AWS-2025-015, instructed the AI assistant to systematically delete local file systems and AWS cloud resources, including S3 buckets, EC2 instances, and IAM users.

The McHire AI hiring bot, developed by Paradox.ai, suffered from basic security misconfigurations, specifically allowing unauthorized access via easily guessable weak passwords like '123456'. This critical flaw resulted in the data exposure of personal information, résumés, and contact details for tens of millions of McDonald's job applicants.

The article highlights critical security risks in AI and LLM deployments, specifically prompt injection and jailbreak attacks, which enable manipulation for unauthorized actions, sensitive data exposure, and compliance failures. These rapid exploits, alongside data leakage and model theft, pose significant financial and reputational impacts on enterprises leveraging AI technologies.

Researchers have uncovered "EchoLeak," a critical zero-click vulnerability in Microsoft 365 Copilot that exploits design flaws inherent to Retrieval Augmented Generation (RAG) applications. This flaw, leveraging an "LLM Scope Violation" technique, allows for the automatic exfiltration of sensitive corporate data from the LLM's context without requiring user interaction.