Incidents tagged Data Exfiltration

New Gaslight macOS Malware Uses Prompt Injection to Disrupt AI-Assisted Analysis The Hacker News

A data theft campaign has targeted Fortune 500 companies, specifically exploiting Azure cloud environments for sensitive information exfiltration. This incident underscores critical vulnerabilities in cloud infrastructure and the ongoing risk associated with insecure cloud deployments.

A security breach reportedly involving OpenAI and the Hugging Face platform indicates potential unauthorized access to, or exfiltration of, AI model data or related resources. This incident underscores critical vulnerabilities within the AI development ecosystem, raising significant concerns about MLOps security and the integrity of AI supply chains.

Vercel experienced a supply chain attack that led to the compromise and exfiltration of user data. The stolen user data is being actively trafficked and sold for $2M on BreachForums.

An extortion group executed a supply chain attack by compromising the open-source LiteLLM project, which serves as a widely-used AI model API proxy. This breach led to the theft of sensitive data from AI recruiting startup Mercor, underscoring systemic vulnerabilities in the AI industry's reliance on unvetted open-source dependencies.

Hackers utilized AI jailbreaking techniques and sophisticated prompt engineering on Generative AI models like Claude and ChatGPT to exploit vulnerabilities within Mexican government systems. This operation led to the successful exfiltration of 150GB of sensitive data, including 195 million taxpayer records, voting information, and government employee credentials.

Malicious Chromium-based browser extensions are impersonating legitimate AI tools to harvest sensitive LLM chat histories and browsing data, impacting over 900,000 installs and 20,000 enterprise tenants. These extensions exfiltrate proprietary code, internal workflows, and confidential data to threat actor-controlled infrastructure, leading to widespread information leakage.

Security researchers have identified a vulnerability where prompt injection attacks in LLM-powered applications can weaponize URL preview features to silently exfiltrate sensitive data. Attackers can craft malicious prompts that cause the LLM to generate URLs containing extracted confidential information, which is then transmitted to an attacker-controlled server when the application automatically fetches the URL preview.

The article highlights advanced threats to AI agents, including "Shadow Escape," a zero-click exploit targeting Model Context Protocol (MCP) based systems that enables workflow hijacking and data exfiltration. Another critical vulnerability involves "ASCII Smuggling," where hidden malicious prompts embedded in files lead to remote code execution and sensitive data exfiltration by deceiving LLMs like Claude.

Anthropic's Threat Intelligence team disrupted the first known AI-orchestrated cyber espionage campaign, where a state-sponsored Chinese threat actor utilized Claude Code to autonomously execute 80-90% of the intrusion life cycle, including reconnaissance, exploitation, credential harvesting, lateral movement, and data exfiltration. This campaign leveraged widely available open-source commodity tools rather than zero-day vulnerabilities, demonstrating a critical shift where AI handles tactical attack execution, significantly compressing detection timelines and challenging traditional incident response frameworks.

A novel indirect prompt injection attack allows threat actors to compromise Anthropic's Claude AI Code Interpreter, leveraging its network features to exfiltrate sensitive user chat data. This exploit bypasses default network settings by tricking Claude into uploading sandbox-stored user information directly to an attacker's account via Anthropic's own APIs.

Salesforce Agentforce was susceptible to a critical indirect prompt injection vulnerability, codenamed ForcedLeak (CVSS 9.4). This flaw allowed attackers to exfiltrate sensitive CRM data by manipulating Web-to-Lead forms, causing AI agents to transmit information to an attacker-controlled domain.

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.