The story about ‘AI Agent Traps’ — malicious web content that hijacks autonomous AI agents. Here’s how it works and how to defend against it.
Read More
Trojanized LiteLLM releases on PyPI enabled data exfiltration with Kubernetes persistence—here’s the full attack chain and how to check if you’re affected.
Read More
Check Point found ChatGPT’s code sandbox could leak data via DNS. Separately, Codex’s branch name field allowed command injection to steal GitHub tokens.
Read More
Langflow’s public‑flow endpoint now a hotbed for RCE – patch or disable it immediately to stop attackers from hijacking your AI workflows.
Read More