Cisco and the cybersecurity agency CISA on Wednesday flagged the exploitation of a Cisco Secure Firewall Management Center (FMC) vulnerability disclosed earlier this year. The security hole, tracked as CVE-2026-20079, is a critical authentication bypass issue that a remote, unauthenticated… Read More "Organizations Warned of Cisco Secure FMC Exploitation"
Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6
Anthropic on Wednesday disclosed a fourth incident in which its artificial intelligence (AI) model broke into real third-party systems, marking the latest in a growing list of cases that have raised concerns about the security risks posed by autonomous AI… Read More "Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6"
Post-quantum cryptography: How to prepare for 2030
Run that comparison against your own data instead of against an industry average. A retail transaction log with a two-year retention window carries a different risk profile than genomic data, merger documentation or infrastructure design specs that need to stay… Read More "Post-quantum cryptography: How to prepare for 2030"
Safe word: What is it and why do you need one?
AI scams are now hyper-realistic. But there’s one simple way to see through them. 09 Sep 2026 • , 5 min. read AI voice scams are no longer as niche as they once were. The technology is both cheap and… Read More "Safe word: What is it and why do you need one?"
Anthropic Reveals Yet Another Cybersecurity Incident
Anthropic has revealed a fourth incident where one of its models accessed a third-party system without authorization. It shared the news in a lengthy “alignment assessment” blog post on September 9. It comes on top of the three incidents revealed in… Read More "Anthropic Reveals Yet Another Cybersecurity Incident"
Nearly 1 in 10 Exposed LiteLLM Gateways Accepted the Example “sk-1234” Admin Key
Nearly one in ten of the internet-facing LiteLLM servers that Wiz Research scanned in February accepted sk-1234, the example admin key in LiteLLM’s own setup guide. LiteLLM is an open-source AI gateway, the software a company puts between its applications… Read More "Nearly 1 in 10 Exposed LiteLLM Gateways Accepted the Example “sk-1234” Admin Key"
10 most critical LLM vulnerabilities
Require outputs to be grounded in authoritative sources and verify claims before acting. Introduce approval workflows and system checks. Log claims, evidence, and outcomes, and test adversarial scenarios. Regularly test workflows against misleading scenarios. Apply least privilege, sandboxing, and rate… Read More "10 most critical LLM vulnerabilities"
ZeroTokens Phishing Platform Steers Attacks in Real Time
A phishing platform dubbed ZeroTokens allows attackers live visibility into victim sessions and the ability to change subsequent prompts in real time, allowing attacks to adapt in real time while targeting credentials and financial information. The platform allowed an operator… Read More "ZeroTokens Phishing Platform Steers Attacks in Real Time"
OFAC Sanctions Chinese Scam Platform Xinbi Guarantee
The US government has followed the UK in sanctioning a notorious Chinese-language marketplace used to support fraud, money laundering and other criminal activity. Xinbi Guarantee connects scam center operators in Southeast Asia and elsewhere, as well as other transnational crime… Read More "OFAC Sanctions Chinese Scam Platform Xinbi Guarantee"
New ‘ShieldCrash’ Zero-Day Exploit Targets Microsoft Defender
The security researcher known as Nightmare Eclipse has released another Microsoft Defender zero-day exploit, right after Microsoft’s record-breaking September 2026 patches. Dubbed ‘ShieldCrash’, the exploit targets fully patched Windows systems for privilege escalation. The proof-of-concept (PoC) exploit code demonstrates an… Read More "New ‘ShieldCrash’ Zero-Day Exploit Targets Microsoft Defender"