Story
arxiv_agent_systems_research ยท Nov 12, 2026 ยท paper
Source brief
Only as Safe as the Weakest Agent: A Break That Appears Only When the System Is Multi-Agent
arxiv.orgNov 12, 2026
original source linked
In brief
Major industry multi-agent systems like Codex and Claude Code can be broken by attacks that have long been unsuccessful against modern frontier models. AI Safety as a discipline has largely focused on finding the boun...
Feed lens
agenticharnesscodexclaude code