Artificial Intelligence
The personalized versions of ChatGPT were used to impersonate legitimate products and trick users into executing PowerShell commands.
Hi, what are you looking for?
SecurityWeek
All posts tagged "ChatGPT"
Artificial Intelligence
Hacktron researchers earned a bug bounty after demonstrating access to OpenAI employee accounts.
Artificial Intelligence
AgentForger allows an attacker to create, insert and remotely control an invisible autonomous AI agent inside a victim organization.
Artificial Intelligence
Advanced Account Security provides stronger login methods, more secure account recovery, shorter sessions, and training exclusion.
Artificial Intelligence
Marketed as ChatGPT enhancement and productivity tools, the extensions allow the threat actor to access the victim's ChatGPT data.
Artificial Intelligence
Radware bypassed ChatGPT’s protections to exfiltrate user data and implant a persistent logic into the agent’s long-term memory.
Artificial Intelligence
A researcher found a way to exploit an SSRF vulnerability related to custom GPTs to obtain an Azure access token.
Artificial Intelligence
Tenable researchers discovered seven vulnerabilities, including ones affecting the latest GPT model.
Artificial Intelligence
Researchers have discovered that a prompt can be disguised as an url, and accepted by Atlas as an url in the omnibox.
Artificial Intelligence
The AI agent was able to solve different types of CAPTCHAs and adjusted its cursor movements to better mimic human behavior.
Artificial Intelligence
OpenAI has fixed this zero-click attack method called ShadowLeak by researchers.
Artificial Intelligence
Researchers show how a crafted calendar invite can trigger ChatGPT to exfiltrate sensitive emails.
Artificial Intelligence
Instead of GPT-5 Pro, your query could be quietly redirected to an older, weaker model, opening the door to jailbreaks, hallucinations, and unsafe outputs.
Artificial Intelligence
Researchers demonstrate how multi-turn “storytelling” attacks bypass prompt-level filters, exposing systemic weaknesses in GPT-5’s defenses.
Artificial Intelligence
Zenity has shown how AI assistants such as ChatGPT, Copilot, Cursor, Gemini, and Salesforce Einstein can be abused using specially crafted prompts.
Artificial Intelligence
LayerX has disclosed an AI chatbot hacking method via web browser extensions it has named ‘man-in-the-prompt’.
Artificial Intelligence
OpenAI has raised its maximum bug bounty payout to $100,000 (up from $20,000) for high-impact flaws in its infrastructure and products.
Artificial Intelligence
A year-old vulnerability in a third-party ChatGPT tool is being exploited against financial entities and US government organizations.
Artificial Intelligence
OpenAI has banned ChatGPT accounts used by Chinese threat actors, including ones leveraged for the development of spying tools.
Artificial Intelligence
DeepSeek’s susceptibility to jailbreaks has been compared by Cisco to other popular AI models, including from Meta, OpenAI and Google.
Artificial Intelligence
An unreleased OpenAI cyber model found and exploited 948 distinct Linux kernel privilege escalation bugs for about $1.2 million.
Artificial Intelligence
Artificial Intelligence
Malware & Threats
Phishing
More than 200 sites were seen serving phishing content to first-time visitors but not to those who revisit.
Vulnerabilities
Artificial Intelligence
