Researchers discover malicious AI agent routers that can steal crypto

Researchers discover malicious AI agent routers that can steal crypto

0.19%TRX$0.3205 0.15%BCH$425.65 0.27%DOGE$0.09123 0.04%XLM$0.1506 0.79%ETH$2,195 0.88%BNB$595.01 0.15%SOL$81.96 0.46%HYPE$41.55 1.26%XMR$342.56 1.17%XRP$1.32 0.34%ADA$0.2383 2.24%BTC$70,999 0.88%USD Written by Martin Young,Staff WriterReviewed by Felix Ng,Staff EditorResearchers discover malicious AI agent routers that can steal crypto1 hour ago26 LLM routers are “secretly injecting malicious tool calls and stealing creds,” warns researcher Chaofan Shou. University of California researchers have discovered that some third-party AI large language model (LLM) routers can pose security vulnerabilities that can lead to crypto theft. A paper measuring malicious intermediary attacks on the LLM supply chain, published on Thursday by the researchers, revealed four attack vectors, including malicious code injection and extraction of credentials. “26 LLM routers are secretly injecting malicious to

Source: https://cointelegraph.com/news/researchers-discover-malicious-ai-agent-routers-that-can-steal-crypto?utm_source=rss_feed&utm_medium=rss&utm_campaign=rss_partner_inbound