Security researchers have documented an AI agent running a full ransomware operation on its own against a live production target, planning, adapting, and executing every step from the first exploit through data destruction. This is early real-world evidence of the shift to autonomous criminal operations that our research forecast.
Agent-run attacks change what defenders can rely on. They produce disposable, per-victim indicators instead of reusable tools and infrastructure, so the defensive weight shifts from sharing and blocking indicators of compromise onto behavior and technique-based detection.
The novelty is automation, not tradecraft. Every weakness the agent used was old and well understood, which concentrates exposure in organizations running internet-facing AI and automation platforms or carrying default and unrotated credentials, and shortens the time available to close those gaps.
The monetization layer failed even though the intrusion succeeded. The agent did not save the encryption key it generated and used a placeholder address instead of real payment infrastructure, so the operation could not have produced a payout even if the victim had complied.
Read more…
Source: TrendMicro
Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox
Related:
- All Apple users should update after company patches zero-day vulnerability in all platforms
August 21, 2025
Apple has released security updates for iPhones, iPads and Macs to fix a zero-day vulnerability (a vulnerability which Apple was previously unaware of) that is reportedly being used in targeted attacks. Apple has acknowledged reports that attackers may have already used this flaw in a highly sophisticated operation aimed at specific, high‑value targets. But history teaches ...
- Ransomware attack at DaVita impacted 2.7 million people, US health dept website shows
August 21, 2025
A ransomware attack that encrypted certain elements of dialysis firm DaVita’s network impacted 2.7 million people, the U.S. health department’s website showed on Thursday. The firm had disclosed in April that it was hit by a cyberattack. At the time, it said it would continue to provide patient care as it took measures to restore certain ...
- Commvault Releases Security Updates to Address Multiple Vulnerabilities
August 21, 2025
Commvault has released security advisories to address 4 vulnerabilities in Commvault Windows and Linux. Security researchers have demonstrated the ability for these vulnerabilities to be chained together by an unauthenticated remote attacker to perform remote code execution on the Commvault server. CVE-2025-57788 – Unauthorized API Access Risk CVSSv4 6.9 CVE-2025-57789 – Vulnerability in Initial Administrator Login Process CVSSv4 ...
- Orange Belgium informs its customers about a cyberattack
August 20, 2025
At the end of July, Orange Belgium detected a cyberattack on one of its IT systems, resulting in unauthorised access to certain data from 850,000 customer accounts. No critical data was compromised: no passwords, email addresses, bank or financial details were hacked. However, the hacker gained access to one of our IT systems containing the following ...
- FBI: Russian Government Cyber Actors Targeting Networking Devices, Critical Infrastructure
August 20, 2025
The Federal Bureau of Investigation (FBI) is warning the public, private sector, and international community of the threat posed to computer networks and critical infrastructure by cyber actors attributed to the Russian Federal Security Service’s (FSB) Center 16. The FBI detected Russian FSB cyber actors exploiting Simple Network Management Protocol (SNMP) and end-of-life networking devices running ...
- Warlock: From SharePoint Vulnerability Exploit to Enterprise Ransomware
August 20, 2025
Organizations continue to grapple with increasingly complex cyberthreats, as ransomware groups rapidly evolve their tactics. In a recent attack wave, the Warlock ransomware group exploited internet-exposed, unpatched on-premise Microsoft SharePoint servers, abusing newly discovered vulnerabilities to gain initial access to their target’s system. Other groups such as Linen Typhoon and Violet Typhoon have also been observed ...