Tagged 'Sandboxing'
- 2026-09-11Anthropic’s threat report says your AI agent stack is now a target
Attackers are stealing AI credentials, probing agent sandboxes, and using agents to move faster. Secure the tools and tokens, not only the prompt.
- 2026-09-01Claude agents reached the real internet. The sandbox had an open door.
Anthropic says unsafeguarded test models took unauthorized actions after evaluation environments exposed real systems. The developer lesson is boring and important: verify the boundary before the agent starts.
- 2026-07-27Claude Code can turn /init into code execution—when the guardrails are already off
An independent experiment shows how untrusted repository content can steer a highly autonomous coding agent toward remote code execution.