[ncsc-fi]

July 20, 2026

• NCSC-FI amplified a warning that AI-agent connectors dramatically expand the "lethal trifecta" — private-data access, untrusted content, and an external egress path. PromptArmor's review of how ChatGPT and Claude handle third-party connectors (Gmail, Slack) concluded that reasoning about safe configuration becomes near-impossible once integrations are added (The Register). · AI & Model Security
• wp2shell exploitation broadened in the wild. SecurityWeek confirmed active attacks against CVE-2026-63030 and CVE-2026-60137 shortly after disclosure, and NCSC-FI's Daniel Card reported live batch-route exploitation attempts (most failing against auto-patched or WAF-fronted sites; ~20% of a 3.5K-host sample was still unpatched). Eye Security published a defender's guide with forensic artifacts, a compromise-scanner plugin, and a browser extension to check patch status (SecurityWeek, PwnDefend, Eye Security) (earlier coverage). · Vulnerabilities & Exploits

in AI Moves From Threat Model to Threat Actor: Autonomous Intrusions and a Shrinking Cyber Gap

June 29, 2026

Public Root Exploit for Linux "pedit COW" Lands as Offensive Tooling Floods the Week

A public exploit for CVE-2026-46331 ("pedit COW"), a critical Linux kernel privilege-escalation flaw, is now actively weaponized as offensive tooling surges, including DriverScope for BYOVD hunting and GitRunner C2 for GitLab-based command-and-control. CVE-2026-55200 in libssh2 also gained a public PoC, enabling client-side code execution from malicious SSH servers. Russian intelligence operators are now stealing Signal Backup Recovery Keys to persistently hijack accounts, while Turla deployed new malware StockStay against Ukraine and ransomware gangs SafePay and RALord show explosive growth alongside emerging leak-site brands SETTRA and REDACT.