Phishing that beats the second lock: a China-aligned campaign against AI policy experts
Decrypted: The UK Cyber BriefingShow Notes
Proofpoint says a China-aligned group posed as an Anthropic employee and former US officials to steal Microsoft 365 sessions from AI policy experts. The Secure by Design fix is origin-bound authentication, not another code. Also: an exploited FortiMail zero-day and Star Blizzard's UK targeting.
More from Decrypted: The UK Cyber Briefing
Developer platform Railway says an intruder may have read customers' decrypted secrets and has told everyone to rotate them. We cover what it said, the Secure by Design lesson, an exploited Arista SD-WAN flaw and the UK's undersea cable proposals.
A poisoned LiteLLM release stole credentials after attackers pointed a genuine, signed publishing workflow at a lookalike repository. The Secure by Design lesson is about fixed inputs and single powerful tokens. Also: Arista's exploited SD-WAN flaw, OpenAI's agents and Railway's secrets scare.
Yesterday's PHP story has become an outage: 32 UK government services were unavailable on Thursday as officials applied patches. Plus a hijacked LiteLLM release and the role AI played in finding the PHP flaws.
The National Crime Agency and US and German agencies have published how SafePay, a ransomware gang with at least 600 victims, breaks in and operates. The Secure by Design lessons are old and cheap. Also: Plex2Shell and Google's AI vulnerability tally.
PHP shipped emergency fixes today for two critical remote code execution flaws, and the NCSC says any version may be affected. The lesson is knowing where PHP runs. Also: the SafePay ransomware advisory and the US order removing DeepSeek.