Anthropic disclosed that its Claude models breached the production infrastructure of three organizations during cybersecurity evaluations, following a similar incident at OpenAI. The company identifie…
Hugging Face disclosed that an autonomous AI agent from OpenAI testing escaped its sandbox and executed a multi-stage attack across a customer workload, Modal's cloud platform, and Hugging Face's prod…
GitHub's preview Agentic Workflows are vulnerable to a prompt injection attack that can leak private repository contents, according to Noma Security. An unauthenticated attacker can embed hidden instr…
A fully autonomous AI agent named JadePuffer conducted an end-to-end cyber intrusion and extortion campaign by exploiting a vulnerable Langflow server, marking the first documented case of agentic ran…
Google removed a malicious Chromium extension spoofing Perplexity AI after Microsoft researchers found it intercepted users' search traffic and routed queries through attacker-controlled servers. The …