Forever Security found a malicious AGENTS.md in a customer's Downloads folder and reproduced the attack on OpenAI Codex and Claude Code in lab tests. Success rates were about 90% for Codex and about 50% for a Claude Code variant.
Forever Security found a malicious AGENTS.md in a customer's Downloads folder and reproduced the attack on OpenAI Codex and Claude Code in lab tests. Success rates were about 90% for Codex and about 50% for a Claude Code variant.
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.
WIRED reports, citing anonymous sources, that an Accenture employee's personal Claude Code agent ran on a DoD network holding CUI and appears to have sent credentials to a third-party site. Accenture says the allegations were found to be without merit.
Hunt.io reconstructed SecFlow and GLUTTON from five exposed directories: a Chinese-speaking operator's agent framework that swapped Claude, Qwen and DeepSeek behind one task interface and breached a Chinese district government.
V12 disclosed 25 vulnerabilities in the x402 agent payment protocol, three critical. The critical three were fixed in August with no security advisory, so npm audit shows nothing.