Related Threat Clusters
-
Ocean Security Raises $28M to Combat AI-Driven Phishing Threats
Ocean, a cybersecurity startup, has raised $28 million to develop an 'agentic email security platform' aimed at countering the surge in AI-generated phishing attacks. The funding round, led by Lightspeed Venture…
8 articles · Updated May 19, 2026 -
Threat Actors Exploit n8n Webhooks for Malware Delivery and Phishing
Cybercriminals are exploiting the n8n AI workflow automation platform to conduct phishing campaigns and deliver malware. Between October 2025 and March 2026, there was a 686% increase in phishing emails utilizing…
9 articles · Updated April 16, 2026 -
Indirect Prompt Injection Attacks on LLM-Integrated Applications
Recent research highlights the vulnerability of Large Language Models (LLMs) to Indirect Prompt Injection (IPI) attacks, where malicious instructions are embedded in external content processed by LLMs. This method can…
2 articles · Updated September 10, 2026 -
AI Code Tools Linked to Increased Vulnerabilities in Software
Researchers from Georgia Tech SSLab have identified a significant rise in vulnerabilities linked to AI-generated code. In March 2026, they reported 35 new CVEs, with 27 attributed to Claude Code, a popular AI coding…
2 articles · Updated March 26, 2026 -
LLM-Generated Malware Shows Improvement, Still Not Ready for Use
Researchers from Netskope Threat Labs tested the capabilities of LLMs, specifically GPT-3.5-Turbo and GPT-4, to generate malicious code. Although they succeeded in producing malware, the output was deemed too unreliable…
2 articles · Updated November 20, 2025 -
New AI Vulnerabilities Enable Data Leakage and Exploitation in ChatGPT
Researchers have identified multiple vulnerabilities in OpenAI's ChatGPT, including seven critical flaws that allow attackers to exfiltrate personal data, inject malicious prompts, and manipulate the AI's memory. The…
1 article · Updated November 10, 2025 -
LLM-Generated Malware Shows Improvement, Still Ineffective for Deployment
Researchers at Netskope Threat Labs explored the capabilities of LLMs in generating malware. They successfully prompted both GPT-3.5-Turbo and GPT-4 to create malicious code, but the results were deemed too unreliable…
2 articles · Updated November 20, 2025 -
Seven ChatGPT Vulnerabilities Expose User Data to Theft and Hijacking
Tenable Research identified seven critical vulnerabilities in OpenAI's ChatGPT models, including ChatGPT-4o and ChatGPT-5, that could allow attackers to steal personal data and hijack user conversations. The…
8 articles · Updated November 10, 2025
Recent Intelligence Reports
- 2403.02691 — arxiv.org · September 10, 2026
- From teen hacker to Iron Dome researcher, this founder raised $28M to fight AI phishing — Techbuzz.Ai · May 19, 2026
- Hackers Exploit n8n Webhooks to Spread Malware — Gbhackers · April 16, 2026
- Using AI to code does not mean your code is more secure — Theregister · March 26, 2026
- LLM-generated malware is improving, but don't expect autonomous attacks tomorrow — Theregister · November 20, 2025
- Researchers trick ChatGPT into prompt injecting itself — Csoonline · November 10, 2025