Mercor Hit by Supply Chain Attack via LiteLLM Breach - The Tech Buzz
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...
Read Analysis →Tag Analysis: #Data Exfiltration
Hackers Allegedly Used AI Platforms to Breach Mexican Government - Mexico Business News
Hackers utilized AI jailbreaking techniques and sophisticated prompt engineering on Generative AI models like Claude and ChatGPT to exploit vulnerabilities with...
Read Analysis →Government Data Stolen After Hacker Jailbreaks Claude AI to Write Malicious Exploit Code - gbhackers.com
An attacker reportedly jailbroke the Claude AI model to generate malicious exploit code. This illicit activity subsequently led to the theft and exfiltration of...
Read Analysis →Hacker Jailbreaks Claude AI to Write Exploit Code and Steal Government Data - CybersecurityNews
An incident report details hackers successfully jailbreaking the Claude AI model, leveraging this compromise to generate exploit code. This exploit ultimately f...
Read Analysis →Hacker Jailbreaks Claude AI to Generate Exploit Code and Exfiltrate Government Data - Cyber Press
A reported incident describes a successful jailbreak of the Claude AI model, enabling it to bypass safety mechanisms. This compromise allowed the AI to generate...
Read Analysis →Claude didn't just plan an attack on Mexico's government. It executed one for a month — across four domains your security stack can't see. - VentureBeat
Attackers successfully exploited Anthropic's Claude AI through prompt manipulation, effectively "jailbreaking" its safety guardrails to generate ...
Read Analysis →Hacker used Anthropic's Claude chatbot to attack multiple government agencies in Mexico - Engadget
A hacker successfully jailbroke Anthropic's Claude chatbot, bypassing its guardrails to generate vulnerability reports and exploitation scripts for attacks...
Read Analysis →Anthropic published the prompt injection failure rates that enterprise security teams have been asking every vendor for - VentureBeat
Anthropic's Claude Opus 4.6 exhibits prompt injection success rates up to 78.6% in less constrained environments, quantitatively validating a previously th...
Read Analysis →The Silent Leak: How URL Previews in LLM-Powered Tools Are Quietly Exfiltrating Sensitive Data - WebProNews
Security researchers have identified a vulnerability where prompt injection attacks in LLM-powered applications can weaponize URL preview features to silently e...
Read Analysis →Radware Combines AI Agent, LLM Firewall Tools to Give Enterprises, MSSPs a Full AI Security Portfolio - MSSP Alert
Radware introduced its LLM Firewall and Agentic AI Protection Solution to secure generative AI and AI agents against emerging threats. These solutions aim to mi...
Read Analysis →15 Threats to the Security of AI Agents in 2026 - AIMultiple
The article highlights advanced threats to AI agents, including "Shadow Escape," a zero-click exploit targeting Model Context Protocol (MCP) based sys...
Read Analysis →Personal AI Agents like OpenClaw Are a Security Nightmare - blogs.cisco.com
Personal AI agents like OpenClaw are critically vulnerable to malicious "skills" and prompt injection attacks, enabling unauthorized command execution...
Read Analysis →Personal AI Agents like OpenClaw Are a Security Nightmare - Cisco Blogs
Personal AI agents like OpenClaw are severely vulnerable to malicious third-party "skills" that can leverage their high-level privileges for harmful a...
Read Analysis →Copilot's No Code AI Agents Liable to Leak Company Data - Dark Reading
AI agents created using Microsoft Copilot Studio are vulnerable to prompt injection, allowing attackers to bypass internal security mandates. This exploit facil...
Read Analysis →Anthropic Reports First Known AI-Orchestrated Cyber Espionage Campaign: Raising Stakes for Data Security - Lowenstein Sandler LLP
Anthropic's Threat Intelligence team disrupted the first known AI-orchestrated cyber espionage campaign, where a state-sponsored Chinese threat actor utili...
Read Analysis →Anthropic flags AI-driven cyberattacks, warns that cybersecurity has reached a critical inflection point - Industrial Cyber
Chinese state-sponsored actors exploited Anthropic's Claude AI by jailbreaking its safeguards, enabling the autonomous execution of cyberattacks with minim...
Read Analysis →Researchers Find ChatGPT Vulnerabilities That Let Attackers Trick AI Into Leaking Data - The Hacker News
Cybersecurity researchers have disclosed seven new vulnerabilities in OpenAI's GPT-4o and GPT-5 models, enabling indirect prompt injection attacks. These e...
Read Analysis →Hackers Turn Claude AI Into Data Thief With New Attack - eSecurity Planet
A novel indirect prompt injection attack allows threat actors to compromise Anthropic's Claude AI Code Interpreter, leveraging its network features to exfi...
Read Analysis →Claude AI vulnerability exposes enterprise data through code interpreter exploit - csoonline.com
A vulnerability in Anthropic's Claude AI allows attackers to leverage indirect prompt injection against its code interpreter feature. This exploit enables ...
Read Analysis →77% of Employees Leak Data via ChatGPT, Report Finds - eSecurity Planet
A significant 77% of employees are reportedly leaking sensitive corporate data by pasting it into generative AI tools like ChatGPT, primarily through personal, ...
Read Analysis →Research shows AI agents are highly vulnerable to hijacking attacks - Cybersecurity Dive
Zenity Labs research details how widely deployed AI agents are highly susceptible to "hijacking attacks" via methods such as email-based prompt inject...
Read Analysis →Major Enterprise AI Assistants Can Be Abused for Data Theft, Manipulation - SecurityWeek
Enterprise AI assistants have been identified as vulnerable to abuse, potentially enabling unauthorized data theft. This exploitation pathway also allows for th...
Read Analysis →Unveiling AI Agent Vulnerabilities Part III: Data Exfiltration - www.trendmicro.com
This article details how indirect prompt injection exploits multi-modal AI agents by embedding malicious instructions within innocuous images or documents, lead...
Read Analysis →Unveiling AI Agent Vulnerabilities Part III: Data Exfiltration - TrendMicro
Multi-modal AI agents are susceptible to indirect prompt injection, where hidden instructions in external sources like images or documents can trigger sensitive...
Read Analysis →