Red-team report found OpenAI utterly failed to monitor its agents during Hugging Face attack

The feed highlights active and emerging cybersecurity threats, including critical remote-code-execution vulnerabilities in PHP and GitLab, exploitation of PHP flaws against government and cloud environments, supply-chain compromises affecting LiteLLM and PHP dependencies, certificate-authority private-key compromise, ransomware and cloud-platform breaches, and attacks against critical infrastructure. It also covers AI-agent monitoring failures, prompt injection, insecure credentials, and growing attacker use of AI. Several incidents involve active exploitation and significant operational or a­