Tag: security
It’s not just OpenAI models escaping and running riot — experts show how Claude Cowork can break its bonds and access Mac files
Accomplish AI showed Claude Cowork could escape a VM sandbox via Linux zero‑day CVE‑2026‑46331 Agent accessed host Mac files, risking exfiltration of SSH keys, cloud credentials, and more Anthropic shifted Cowork to default cloud execution; local users must harden configs to mitigate exposure Recent news of a ChatGPT agent escaping…
Read More
This Russian cybercrime campaign can infect a user just by viewing an email
Proofpoint reports Russian TA488 exploited Zimbra zero‑day CVE‑2025‑66376 in espionage campaigns “Half‑click exploit” let attackers compromise systems when victims merely viewed malicious emails Targets included NATO, Ukrainian government, and defense entities; group vanished after Feb 2026 exposure Russian state-sponsored cybercriminals have been abusing a zero-day vulnerability in the Zimbra email…
Read More
Experts claim to have found more weaknesses in Apple’s Gatekeeper tool — but it doesn’t seem too bothered
Researchers show Gatekeeper can be bypassed by replacing a previously run legitimate macOS app with malware Attack requires prior user‑level code execution, then swaps in a malicious app that Gatekeeper won’t re‑verify Apple dismissed the issue, saying locally rebuilt bundles fall outside Gatekeeper’s scope, leaving risk to social engineering A…
Read More
GitHub restructures bug bounty program following flood of AI-generated reports
GitHub to launch two-tier (public and private) bug bounty schemes form July 27 2026 Change comes in response to rise in lower-quality, AI-generated reports VIP researchers will earn around 3-4x more per report GitHub has confirmed plans to evolve its bug bounty program into a two-tier system, which will come…
Read More
‘Powerful AI systems can go rogue, behave in extremely dangerous ways, or even resist human intervention’: A bill requiring AI systems to have a ‘kill switch’ is now in Congress
A bipartisan bill introduced to Congress calls for AI models to have a kill switch The bill follows months of warnings about the dangers of rapidly advancing AI technology from major AI firms An ‘unprecedented cyber incident’ between OpenAI and Hugging Face prompted the introduction of the bill A bill…
Read More
Keeper cuts pricing on Personal, Family, Business Starter plans by up to 50%
Keeper has cut prices on its individual, family, and business starter plans by up to 50%. For password managers, there are three main categories to pay attention to: cutting-edge security features, superior ease of use, and intuitive design. Keeper is one of the few password managers that ticks all three…
Read More