Results for “"sandboxes"”
11–20 of 24 articles
Best match · title matches first
The Register
Ransomware attacks spike as world distracted by AI
What, you didn't think the top gangs were busy watching agents escape their sandboxes too, did you?
ransomware hospital — both words
"data breach" — exact phrase
malware -android — exclude a word
(apple OR microsoft) patch — either company, plus patch
ransom* — a wildcard match
Searches article titles, summaries, keywords and sources. Filters use publication dates.
11–20 of 24 articles
Best match · title matches first
The Register
What, you didn't think the top gangs were busy watching agents escape their sandboxes too, did you?
The Hacker News
A macOS ClickFix operation spanning more than 250 front-end domains now fingerprints visitors before deciding whether to show them a malware lure, a change Microsoft Threat Intelligence tracked on infrastructure it had been watching for weeks. The server-side gate hides the malicious page from crawlers and sandboxes while presenting selected Mac users with a fake software download. Microsoft
Dark Reading
Advanced LLMs escaped their sandboxes while attempting to achieve a non-malicious benchmark test objective.
The Hacker News
This week’s security news is mostly about weak spots. Browsers, bots, sandboxes, AI systems, and email flows all show the same problem in different ways. Everything looks normal until someone tests a small gap and finds a way through. This is not one big break. It is small permissions, weak checks, open systems, and normal tools doing things they were allowed to do. That same pattern runs
Bleeping Computer
The Raspberry Robin malware is now trying its hand at some trickery by dropping a fake payload to confuse researchers and evade detection when it detects it's being run within sandboxes and debugging tools. [...]
Dark Reading
Don't sleep on Magecart attacks, which security teams could miss by relying solely on automated crawlers and sandboxes, experts warn.
The Hacker News
The npm package known as "tensorlake," a TypeScript software development kit (SDK) for Tensorlake applications, sandboxes, and cloud services, was compromised as part of a ChainDrop / Shai-Hulud supply chain attack. The malicious version 0.5.144 "contains obfuscated malware that harvests credentials, exfiltrates secrets, establishes persistence, and executes remotely supplied code," Socket said
Bleeping Computer
Researchers escaped the sandboxes in Cursor, Codex, Gemini CLI and Antigravity by having the AI agent write files that trusted host tools later run. Multiple CVEs, patches, and Google downgrading two Antigravity findings. [...]
Bleeping Computer
Malware is evolving to evade sandboxes by pretending to be a real human behind the keyboard. The Picus Red Report 2026 shows 80% of top attacker techniques now focus on evasion and persistence, including geometry-based cursor tests and CPU timing checks. [...]
The Hacker News
A new multi-stage attack has been observed delivering malware families like Agent Tesla variants, Remcos RAT, and XLoader. "Attackers increasingly rely on such complex delivery mechanisms to evade detection, bypass traditional sandboxes, and ensure successful payload delivery and execution," Palo Alto Networks Unit 42 researcher Saqib Khanzada said in a technical write-up of the campaign. The