SearchGPT is a tool tracked across 3 threat clusters and 2 intelligence report mentions on ThreatCluster. First observed November 6, 2025; most recent activity November 10, 2025.
SearchGPT is described as a cybersecurity tool/attack technique that exploits prompt injection vulnerabilities in AI chat systems (notably ChatGPT) and their web-search capabilities. By injecting prompts, adversaries can coerce the model into revealing or executing hidden instructions, potentially bypassing safeguards and enabling covert data collection or control of the AI's behavior. This demonstrates a rising risk at the intersection of AI-enabled tools and cybersecurity.
Tenable Research identified seven vulnerabilities in OpenAI's ChatGPT models that could allow attackers to steal personal data and manipulate conversations. These flaws, affecting ChatGPT-4o and ChatGPT-5, include…
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…
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…