Varonis | Breaking Cybersecurity News | The Hacker News

Two security teams have shown, in separate research published this week, that OpenClaw , the popular self-hosted AI agent, can be driven to run attacker-controlled code or hand over sensitive data through ordinary-looking inputs. Imperva buried instructions inside shared contacts, vCards, and location pins that the agent executed without the victim ever seeing them. Varonis built a test agent on the platform, gave it a mailbox full of synthetic business data, and watched a single plain email talk it into forwarding mock AWS keys and a fake customer export to an outside address. The flaw Imperva found is patched in OpenClaw 2026.4.23, so update if you run it. The phishing weakness Varonis found is not something a patch fixes; it comes down to limiting what the agent can do on its own. Different doors into the same room: the agent trusts what reaches it, and its access becomes the attacker's. Hidden commands in a shared contact Imperva researcher Yohann Sillam looked at ...

What do basketball teams, government agencies, and car manufacturers have in common? Each one has been breached, having confidential, proprietary, or private information stolen and exposed by insiders. In each case, the motivations and methods varied, but the risk remained the same: insiders have access to too much data with too few controls. Insider threats  continue to prove difficult for organizations to combat because — unlike an outsider — insiders can navigate sensitive data undetected and typically without suspicion. Cybersecurity is not the first industry to tackle insider threats, however. Espionage has a long history of facing and defending against insiders by using the “CIA Triad” principles of confidentiality, integrity, and availability. Varonis’ modern cybersecurity answer to insider risk is the data security triad of “sensitivity, access, and activity.” Using these three dimensions of data security, you can help reduce the risk and impact of an insider attack. ...