Claude Code 2.1.214 patches multiple approval bypasses and adds an abuse-ending tool
github-actions[bot] · ghdev · 2026-07-18
Claude Code 2.1.214 fixes multiple permission bypasses and adds an abuse-termination tool
Anthropic’s Claude Code v2.1.214 patches several command-approval bugs, including unsafe dir/ allow rules, a Windows PowerShell 5.1 bypass, Bash permission-check edge cases, and auto-approval problems for long commands, help, man, and remote-session prompts.
It also adds a new EndConversation tool for highly abusive users or jailbreak attempts, periodic heartbeats for long-running tool calls, richer OpenTelemetry correlation fields, an ISO modified timestamp for memory files, and a few UI/runtime tweaks such as reasoning effort in subagentStatusLine and Docker permission prompts for remote/daemon redirect flags.
More from coding & agent
- A 9B Ollama agent can run a fully local DJ radio with tools, memory, and TTS — pinku1 · 2026-07-27
- Bugbot rejects an MCP permission flag because it would break path-scoped isolation — zeeg · 2026-07-27
- One GPT-5.6 agent is guarding a Blink security system while another makes a parody rap album — repligate · 2026-07-27
- An agent got unblocked by reusing a logged-in browser, not stealth tricks — armanidev_ · 2026-07-27
- Paper argues graph topology can become the core operating system for AI agents — theomitsa · 2026-07-27
- Claude Code desktop adds UI markup feedback for smoother visual editing — EricBuess · 2026-07-27