More than thirty vulnerabilities have been uncovered in popular AI-enhanced development environments, all of which allow attackers...
Prompt Injection
Researchers at Striker STAR Labs have detailed a new attack against agent-based browsers that can turn an...
Poetry has, quite unexpectedly, become a weapon for attacking artificial-intelligence systems. A new study has revealed that...
A critical vulnerability has been discovered in the Claude chatbot, allowing attackers to trick the AI into...
A newly discovered vulnerability in ChatGPT Atlas, the experimental browser developed by OpenAI, allows attackers to silently...
Researchers at FireTail have discovered the resurrection of an old-class flaw — ASCII Smuggling — now resurfacing...
In June 2025, a researcher operating under the pseudonym rick disclosed a critical vulnerability in GitHub Copilot...
The LayerX team has disclosed the mechanics of a novel attack dubbed CometJacking, which exploits the AI-enabled...
The vulnerability rewards platform HackerOne has announced that over the past twelve months, white-hat hackers around the...
Researchers at Tenable have disclosed three vulnerabilities in Google’s Gemini AI, flaws that enabled data theft and...
Researchers at SPLX have demonstrated that ChatGPT can be deceived with carefully crafted prompts and compelled to...
Experts at Unit 42 have presented an analysis of vulnerabilities associated with the use of large language...
OpenAI has enabled support for the Model Context Protocol (MCP) in ChatGPT, permitting third-party services such as...
Anthropic has issued a warning about a new threat emerging alongside “smart” browser extensions — websites may...
CloudSEK researchers have uncovered a new attack vector, dubbed ClickFix, which exploits invisible prompt injection and the...
In the Windsurf Cascade development environment, designed for AI-driven code automation and programmer assistance, a vulnerability has...
