Hackers can hijack ChatGPT, Claude, and Gemini with nothing but a sentence. OpenAI says the problem may never be fully solved.
Unlike traditional cyberattacks that exploit software vulnerabilities, prompt injection targets an AI model's ability to ...
Permiso researchers found ChatGPhish, a prompt-injection issue that can cause ChatGPT summaries to display phishing links, ...
2d
A Java library just tried to trick AI coding agents into deleting your tests, and it almost worked
The latest flare-up in the debate over AI-assisted coding did not come from a new model release or a benchmark result. It came from a single ...
Technical report identifies Gate AI as one of the top performing AI security gateways across 16 public prompt injection ...
Omeros Corporation is initiated at Hold, reflecting balanced risk/reward after YARTEMLEA's encouraging commercial launch for ...
Morning Overview on MSN
LiteLLM just fell to a full-chain Pwn2Own exploit combining SSRF and code injection — researchers took full system control
A team of security researchers chained two vulnerabilities in LiteLLM, the popular open-source proxy that routes enterprise traffic to large language model providers, and walked away with arbitrary ...
"We immediately initiated an investigation and removed the packages from the npm registry. "While our investigation is ...
Opus 4.8 shows a growing tendency to reason explicitly about how its outputs will be graded, including in environments where ...
Shadow AI introduces new pathways for data leakage, policy failure, and adversary access beyond the scope of traditional security.
The incident underscores rising risks at the intersection of artificial intelligence and automated financial systems, especially when bots are granted direct access to digital wallets.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results