… After 50, the agent falls back on asking permission from the user. The comment explains that 50 is a generous allowance for legitimate usage. "The assumption was correct for human-authored commands," the Adversa AI Red Team said in a writeup provided ahead of publication to The Register . …
… "If they don't publish an advisory, those users may never know they are vulnerable – or under attack." He said the attack probably works on other agents that integrate with GitHub, and GitHub Actions that allow access to tools and secrets, such as Slack bots, Jira agents, email agents, and deployme… …
… Projects like Google's Big Sleep, an AI agent that helps security researchers find zero-day flaws, have spotted several including a previously unknown exploitable memory-safety flaw in the widely-used OpenSSL library. …
… "Safety evaluations may therefore need to examine not just behavior, but the origins of models and training data and the processes used to create them," the paper said. ® ai openai large language model anthropic ai and ml software
… Cherny said that larger contexts are now common because users are "pulling in a large number of skills, or running many agents or background automations." MORE CONTEXT Anthropic goes nude, exposes Claude Code source by accident AMD's AI director slams Claude Code for becoming dumber and lazier sinc… …