The latest AI security developments, threats, and industry updates.
Varonis researchers used the assistant's own refusals to map an undocumented URL parameter in Microsoft Copilot Personal, chaining it into silent access to Gmail, Drive, and Calendar. Microsoft patched CVE-2026-24301 on August 18.
A critical unauthenticated SSRF in MLflow's webhook delivery lets attackers pivot into cloud metadata endpoints and steal credentials. WatchTowr's honeypot network caught scanning starting within hours of the CVE going public.
Barracuda researchers demonstrated at Black Hat 2026 that a single compromised employee account, combined with an integrated AI assistant like Microsoft Copilot, can be weaponised to escalate access to the CEO and facilitate a fraudulent wire transfer -- without introducing any new permissions.
Anthropic has deployed machine-readable watermarks in all Claude outputs globally as of August 2, 2026, implementing two marking methods to satisfy EU AI Act Article 50(2) transparency requirements — right as the enforcement window opens.
OpenAI launched GPT-5.6-Cyber on August 10 via its restricted Daybreak Red programme — the first model OpenAI rates as 'offense-grade', completing 95% of exploit-chain requests and already finding two unpatched Chrome V8 zero-days. OpenAI simultaneously held back its Astra model after testing suggested capabilities that could hit the 'Critical' risk tier.