InfoWorld AI·
In a test of major LLMs, Zscaler found that some autonomous AI agents fell victim to frauds, reinforcing how easily some high-end enterprise agents can be conned by schemes that would fool few, if any, humans. The security vendor looked at various forms of indirect prompt injection (IPI) traps and found that, whereas many models fell victim to the schemes, some of the lower-level LLMs fared better than their pricier siblings. The Zscaler testing found, for example, that four models were found to be “vulnerable”: Llama3-3-70b-instruct; Llama3-2-90b-instruct; Gemini-3-flash; and Gemini-2.5-pro. Three models were found to be “safe”: Llama4-maverick; Gemini-3.1-pro; and Gemini-3.1-flash-lite. Those results indicated that the scam resistance of Gemini-2.5-pro was seemingly weaker than that of Gemini-3.1-flash-lite. But Noah Kenney, principal consultant at Digital 520, said that there is not necessarily any valuable takeaway from that revelation, because agents constantly change behavior a
Read full articleAI vulnerabilities in prompt injection attacks could undermine trust in automated systems, posing significant risks to digital transactions. The post Zscaler researchers identify prompt injection attacks targeting AI agents for crypto payments appeared first on Crypto Briefing.
OKX has launched the beta version of an AI marketplace that allows autonomous agents to find work, complete tasks, receive onchain payments, and build portable reputations across transactions. According to an announcement from OKX, the new platform, called OKX AI,…
The surge in AI token demand by 2030 will reshape infrastructure needs, favoring companies that optimize for persistent, compute-heavy workloads. The post DigitalOcean CEO predicts AI token demand will hit 5 quintillion annually by 2030, driven by autonomous agents appeared first on Crypto Briefing.
AI coding tools' vulnerability to indirect prompt injection necessitates enhanced security measures, posing new risks for developers and organizations. The post New attack exploits Claude Code to hijack developer machines through poisoned repositories appeared first on Crypto Briefing.
Insider Brief General Intuition announced it has raised $320 million in a Series A funding round that values the artificial intelligence startup at $2.3 billion, as the company expands development of AI models designed to train autonomous agents that can act in digital and physical environments. The round was led by Khosla Ventures and included […]
ClickUp's Brain AI could redefine productivity by minimizing human task management, challenging competitors with its autonomous agent approach. The post ClickUp’s Brain AI autonomously creates dedicated agents for tasks appeared first on Crypto Briefing.
CIOs and CISOs have many strategic and operational fears when it comes to unleashing fully-autonomous agents on tasks and hoping that everything works out. Will the agent start to delete critical files? Will the agent go off on a mission tangent and generate a massive token bill for the team when they return the next morning? Will it be tricked by a state actor and engage in malicious actions? To help alleviate those concerns, OpenAI announced on Thursday that it has agreed to acquire Ona, a 79 person cloud development environment (CDE) provider formerly known as Gitpod, to accelerate its efforts to make agentic AI enterprise-friendly. An OpenAI statement said Ona’s technology “provides secure, persistent environments where agents can access the tools, systems, and context they need to make progress over time. By bringing Ona to OpenAI, we will expand Codex beyond work tied to a single device or active session and help more organizations deploy agents securely in production.” An Ona s
Travala has launched an agentic AI travel protocol allowing autonomous agents to book more than 2.2 million hotels with minimal human intervention. Incentives and the Rise of Agentic Commerce Travala on June 5 launched what it calls the world’s first agentic AI travel protocol, allowing autonomous software agents to search, book, and pay for more […]
