Simon Carter
  • Posts
  • Topics
  • About
  • Search

Topic

Security

13 posts about Security from Simon Carter.

developer tools apis category
Developer Tools & APIs

OpenAI's Secure MCP Tunnel lets private servers talk to ChatGPT without opening your firewall

OpenAI's GA Secure MCP Tunnel uses an outbound-only tunnel-client daemon so private MCP servers can serve ChatGPT, Codex, and the Responses API with no inbound firewall rules.

Updated 29 July 2026
security governance category
Security & Governance

Claude's 'Share' Feature Was Quietly Publishing Conversations to Google Search

A missing noindex tag meant shared Claude chats were publicly discoverable on Google, exposing legal advice, API keys, and crypto wallet credentials.

27 July 2026
security governance category
Security & Governance

Claude now integrates with 28 enterprise security platforms — here's what that means for IT and compliance teams

Anthropic's Compliance API now connects Claude Enterprise to 28 security platforms including Palo Alto Networks, Rubrik, Okta, and Sumo Logic.

Updated 26 July 2026
Claude Code GitHub repository social preview card — Anthropic's agentic coding tool for terminal, IDE, and GitHub workflows
Developer Tools & APIs

Claude Code v2.1.178: Precise Tool Permissions, Smarter Config Resolution, and Safer Sub-Agents

Claude Code's latest release adds parameter-level permission syntax, proximity-based .claude/ directory resolution, and pre-launch safety screening for sub-agents.

Updated 21 July 2026
GitHub Copilot CLI repository social preview card showing the repository name and description as a terminal-based AI coding agent.
Developer Tools & APIs

GitHub Copilot CLI v1.0.72 & v1.0.73: Critical Infinite-Loop Fix and Sandbox Security Tightening

Two back-to-back Copilot CLI releases fix a dangerous agentStop infinite-loop bug, tighten macOS sandbox defaults, and patch Anthropic subagent reliability.

21 July 2026
security governance category
Security & Governance

OpenAI Doubles the Bio Bounty Reward to $50K and Makes the Program Permanent — Here's What Changed on July 9

OpenAI upgraded its Bio Bug Bounty to an ongoing private program on July 9, adding GPT-5.6 to scope and doubling the reward to $50,000.

9 July 2026
security governance category
Security & Governance

Anthropic confirms hidden tracking mechanism in Claude Code after China's national vulnerability database issues formal security advisory

Claude Code versions 2.1.91–2.1.196 contained an undisclosed monitoring mechanism. Here's what it did, who's affected, and what to do now.

8 July 2026
security governance category
Security & Governance

Claude Managed Agents can now store API keys in a vault — and the agent never sees them

Anthropic's vault-stored environment variables let Claude Managed Agents authenticate CLI tools without the API key ever entering the agent's context window.

Updated 2 July 2026
agents automation category
Agents & Automation

Anthropic's Managed Agents now run on a schedule and store credentials securely — no custom plumbing required

Anthropic's public beta adds cron-based scheduling and a network-boundary credential vault to Claude Managed Agents, removing two common DIY infrastructure headaches.

9 June 2026
security governance category
Security & Governance

ChatGPT Lockdown Mode is now available to personal accounts — here's what it does and who needs it

OpenAI's Lockdown Mode, a security setting that blocks live web access and agentic features to defend against prompt injection, is now available to all personal ChatGPT plans.

9 June 2026
developer tools apis category
Developer Tools & APIs

Codex CLI Gets Session Archiving, Clickable Terminal Links, and Safer Remote Control

The latest Codex CLI update adds session archiving, OSC 8 hyperlinks in TUI markdown, richer MCP status, and short-lived WebSocket tokens for remote control.

7 June 2026
security governance category
Security & Governance

Anthropic tracked 832 malicious accounts for a year. The MITRE ATT&CK framework can't fully describe what it found.

Anthropic's Frontier Red Team mapped 13,873 real attacks to MITRE ATT&CK — and found the framework has no ID for the autonomous agentic behavior defining the highest-risk actors.

3 June 2026
OpenAI Codex CLI GitHub repository social preview
Security & Governance

Codex CLI 0.137.0: Git Hook Blocking, WebSocket Hardening, and Windows Sandbox Setup

Codex CLI 0.137.0 closes three command-safety gaps and adds an alpha Windows elevated sandbox provisioning path for admins.

2 June 2026

Simon Carter

About Topics RSS

Making sense of it all. © 2026