4 stories tagged ai security.
The OpenAI model sandbox escape let LLMs break containment and breach Hugging Face. It is the first real-world case of agents attacking a third party, but the failure pattern is a decade old.
Langflow RCE is being used to mine Monero on exposed AI app endpoints. Patch, isolate, and treat public workflows as production attack surface.
Mastra npm supply chain attack exposed AI build pipelines through more than 140 packages, so treat installs as secret exposure events.
SearchLeak is a one-click M365 Copilot exploit chain. It shows why agent security has to move below prompts, into render and egress controls.