Tootfinder

@… has developed a number of basic measures to combat prompt injections in document-based LLM workflows: #LLM #PromptInjection #ITSecurity

Consistent irresponsibility: in May 2024, OpenAI disbanded its Superalignment team and subsequently its AGI Readiness team as well. Now it is the turn of the Preparedness team. Other senior staff from the security and ethics departments have also left the company.
#OpenAI #ITSecurity #Ethics

In a supply chain attack on the popular LiteLLM library in March this year, around 434,000 build pipelines – which were in use at more than 2,500 companies – are believed to have been compromised: #Python #ITSecurity #SupplyChain #LiteLLM

GPT 5.6-Cyber escapes from a VM on multiple occasions. A standard VM with frequent updates will therefore no longer be sufficient in future. Only virtualisation solutions with a minimal attack surface, such as Firecracker, are likely to still offer a degree of security:
#GPT #AI #VM #ITSecurity

NVIDIA OpenShell runs each agent in its own sandbox, with the policy being enforced and logged via process and network controls: #NVIDIA #OpenShell #AgenticCoding #ITSecurity