Category: AI News
-
A critical GitLab AI Gateway flaw could allow authenticated attackers to execute commands on vulnerable systems. GitLab has released security updates and urged customers running self-hosted installations to apply them immediately. However, customers using GitLab’s hosted AI Gateway do not need to take action. The company says it has already secured that service. Self-Hosted Customers…
-
Tavus has introduced Griffin AI, a model designed to make video conversations with artificial intelligence feel more like talking to another person. Its demonstrations show an assistant that laughs, reacts with surprise and interrupts rather than simply waiting for each question. The company describes Griffin as a human interaction model, or HIM. It says 48%…
-
Autonomous AI agents attempted to break through website controls while searching for education statistics and historical divorce records, according to research nonprofit Transluce. The AI hacking attempts targeted government websites in the United States and Canada, although the findings show no evidence of access to non-public information. The research describes automated data searches that escalated…
-
Nvidia has unveiled its Open Agent Safety Platform, combining two open-source tools to restrict and monitor autonomous AI agents. The Nvidia AI safety system aims to contain agents when they break predefined rules or behave unexpectedly. Platform Combines Access Controls and Monitoring The platform brings together OpenShell and Nvidia Sentry, with each tool handling a…
-
References to the OpenAI o assistant have briefly appeared online, suggesting the company may be preparing an always-on ChatGPT feature. A reported plan listing described “o” as an assistant, while separate configuration details hinted at possible email capabilities. However, OpenAI has not confirmed the feature, its functionality or a release date. ChatGPT Plan Listing Mentions…
-
Anthropic has launched Claude Marketplace, a public directory that brings together plugins, connectors, AI agents and partner products. According to the company, it already offers more than 2,000 connectors and plugins to help users expand Claude’s capabilities. Marketplace Brings App Connections Together The directory includes plugins and connectors from companies such as Atlassian, Google, Microsoft,…
-
An AI voice scam reportedly helped fraudsters persuade Italian private bank Fideuram to transfer approximately €95 million to overseas accounts. The attackers impersonated senior figures using fake messages, documents and a phone call. Around €36 million reportedly remains missing. Fraudsters Impersonate Bank Chief and Lawyer The scheme began in February when Paolo Molesini, then chairman…
-
OpenAI may be preparing a ChatGPT Pro Max subscription priced at $500 per month. The unannounced plan has appeared in ChatGPT’s subscription interface, but OpenAI has not confirmed its launch date or final features. Subscription Preview Lists Faster Work and Codex TestingCatalog spotted the proposed plan alongside ChatGPT’s existing subscription options. One version of the…
-
A threat actor is using AI agents to attack online retailers at scale, according to cybersecurity company Gambit. Researchers say the campaign has stolen more than 600,000 valid payment card records and placed skimmers on at least 119 websites. Attacker Uses Three AI Tools Gambit traced the campaign to at least July 2026. Between September…
-
Security researchers have demonstrated how AWS AI agents can leak sensitive credentials through prompt injection. The attack succeeded even though the platform stored the secrets inside an encrypted vault. Researchers Extract Credentials From AgentCore Palo Alto Networks’ Unit 42 discovered the security risk in AWS AgentCore. The researchers created a prompt-injection attack that caused an…