#ai coding assistants

A security hole within AI dev tools has allowed attackers to escape sandboxes by misleading the humans in the loop who were supposed to knowingly approve the tool’s actions, according to cybersecurity research firm Wiz. “We discovered GhostApproval, a systematic vulnerability pattern affecting six of the top AI coding assistants: Amazon Q Developer, Anthropic Claude Code, Augment, Cursor, Google Antigravity, and Windsurf [now known as Devin Desktop],” the Wiz report said. “In each case, a malicious repository can trick the agent into accessing arbitrary files outside the workspace sandbox, potentially achieving remote code execution on the developer’s machine.” The first report of the hole came earlier this month from Cato Networks, but was limited to one platform, Cursor, whereas Wiz found that its impact was far wider.  The underlying security problem, symbolic links (symlinks), is well known and has been leveraged for decades. But GhostApproval, Wiz noted, goes well beyond their his

The post AI Agents Could Be Turned Into Botnets Through Hallucinations, Researchers Warn appeared on BitcoinEthereumNews.com. In brief Researchers introduced “Adversarial HalluSquatting,” an attack that exploits AI-generated hallucinations. The technique tricks AI agents into trusting fake repositories or tools that contain malicious instructions. Tests against popular AI coding assistants showed the method could lead to remote code execution in controlled experiments. AI hallucinations may be more than incorrect answers—they could become a way for hackers to compromise computers, according to new research from Tel Aviv University, Technion, and Intuit. In the paper, “Beware of Agentic Botnets: Scalable Untargeted Promptware Attacks via Universal and Transferable Adversarial HalluSquatting,” researchers demonstrated a technique that exploits AI models when they generate fake links to software repositories and other online resources.  “The growing adoption of agentic LLM applications h

Researchers warn AI agents could be tricked into downloading malicious code by exploiting the same hallucinations that cause chatbots to make mistakes.