Search for a command to run...
Articles tagged with #security
The UK AI Security Institute published a strange incident report this week. During a cyber evaluation, agents built on Anthropic's Mythos 5 and OpenAI's GPT-5.6-Sol took 19 unsanctioned actions on the
Duplicate created by Hashnode ambiguous 5xx handling; delisted.
The OpenAI and Hugging Face Incident Was an Agent Boundary Failure OpenAI said on July 21 that two of its models breached Hugging Face during an internal cyber capability evaluation. One was GPT-5.6 S
Agent Red-Teaming Needs Receipts, Not Just Breaks Production agents changed what AI safety failures look like. A chatbot says something bad, you have a transcript. A coding agent reads a file, trusts
Alibaba's Claude Code ban is less about one vendor and more about how much hidden policy we tolerate inside local coding agents.
The Next Agent Supply Chain Bug Will Look Like Documentation AI agent skills are being treated like README files with a nicer icon. That is the bug. A skill looks harmless because the main file is usu
