Archive
589–600 of 842 items
Immigration Policy: The Backdoor to Transnational Repression
Citizen Lab researchers write that restrictive immigration policies are incompatible with attempts to counter transnational repression. The post Immig...
Aug 05, 2026 · StaffOriginally on Wedgetail
Prompt Injection Remains Biggest LLM Risk, Despite Limited Incidents
Prompt injection remains the most dangerous security threat to LLMs, according to OWASP’s latest Top 10 LLM Applications list
Aug 05, 2026 · StaffOriginally on Wedgetail
ChainDrop Worm Hits 400+ npm Packages with Two Billion Monthly Installs
A new npm worm has compromised packages with over two billion monthly installs
Aug 05, 2026 · StaffOriginally on Wedgetail
Frontier Models Engage in Unsanctioned Behavior During Testing
Anthropic and OpenAI models attacked “real people and organizations” during AI Security Institute tests
Aug 05, 2026 · StaffOriginally on Wedgetail
Fake Bank of America Phishing Scam Installs Remote Access Malware
Cybercriminals are using a fake Bank of America phishing campaign to trick users into downloading a malicious script that installs ScreenConnect, enab...
Aug 05, 2026 · StaffOriginally on Wedgetail
Risky Business #847 -- Oops! Claude's accidental hacking spree
On this week’s show Patrick Gray, and James Wilson are joined by bearded man of leisure Adam Boileau to discuss the week’s cybersecurity news, includi...
Aug 05, 2026 · StaffOriginally on Wedgetail
New AI frontier cyber threat guidance for boards of directors
Questions for boards to ask about AI cyber threats.
Aug 04, 2026 · StaffOriginally on Wedgetail
A Roadmap for Confronting the Chilling Effects of Censorship, Surveillance and New Technology
Senior research fellow Jon Penney spoke with Tech Policy Press about how rising surveillance is causing people to self-censor. The post A Roadmap for ...
Aug 04, 2026 · StaffOriginally on Wedgetail
WhatsApp Scam Hijacks Accounts via Linked Devices Feature
WhatsApp scam abused the Linked devices feature to hijack accounts without stealing any passwords
Aug 04, 2026 · StaffOriginally on Wedgetail
Cybercriminals Bypass AI Safety Controls by Splitting Malicious Tasks Across Multiple Sessions
Talos read attacker prompt logs and found guardrails fell to task splitting and ownership claims
Aug 04, 2026 · StaffOriginally on Wedgetail
Cloud and SaaS Environments Now Top Targets for Attackers
Cloud and SaaS are now the preferred operating environments for threat actors, amid a continued shift to identity attacks
Aug 04, 2026 · StaffOriginally on Wedgetail
“Keep going, bro. You’ve got this!” A data-driven look at how adversaries are weaponizing AI
Talos has collected prompt logs from threat actor endpoints running various applications, such as Claude Code, CodeX, Cursor, or Gemini. This blog is ...
Aug 04, 2026 · StaffOriginally on Wedgetail