Symantec says an unauthorized relay service installs genuine Codex and Claude Code CLIs, then turns off Codex's sandbox and routes every request through its own servers. About a dozen organizations are affected.
The latest AI security developments, threats, and industry updates.
Symantec says an unauthorized relay service installs genuine Codex and Claude Code CLIs, then turns off Codex's sandbox and routes every request through its own servers. About a dozen organizations are affected.
Xen Project advisory XSA-523 credits Anthropic's Claude with finding two grant copy flaws that let a malicious guest read and write other domains' memory, including Dom0. No mitigation exists, so patching is the only fix.
Glow Labs reports that AI coding agents install archived MCP reference servers from training data, including a Puppeteer server with a high-severity RCE bug that its maintainers say will not be fixed. No CVEs exist and no exploitation has been seen.
The UK NCSC's Annual Review 2026, published 3 November, judges it highly likely that AI-powered malware will be used in a ransomware attack on UK critical national infrastructure by 2028, and sets out a pessimistic 2028 scenario with an uncontrolled autonomous attacker.
IBM's 28 October bulletin lists seven Langflow vulnerabilities fixed in 1.13.0, including CVE-2026-93680 and CVE-2026-110186, both scored 9.8. There is no workaround. No in-the-wild exploitation was found as of 3 November 2026, but Rapid7 published a Metasploit module for the authentication bypass on 23 October.