Blog

No posts here yet.

• Security for Claude Code Development

  Claude Code runs in your terminal with your permissions. This post covers the risks, the 2026 incidents that began when a developer opened a repository, their impact, and the settings, hooks, checks and habits that control them.

  claude-codecoding-agentsagentsprompt-injectionleast-privilegesandboxing
  AISecurityLabs.orgUpdated 30 Sept 20267 min read

• Security for Codex Development

  OpenAI Codex runs commands on your machine with your permissions. This post covers the risks, the CVEs that began with opening a repository, their impact, and the configuration, rules, checks and habits that control them.

  codexopenaicoding-agentsagentsprompt-injectionleast-privilege
  AISecurityLabs.orgUpdated 30 Sept 20268 min read

• Security for Copilot Development

  GitHub Copilot's agents run commands with your permissions. This post covers the risks, the incidents that turned injected text into commands, their impact, and the settings, checks and habits that control them.

  github-copilotcoding-agentsprompt-injectionleast-privilegesandboxingsupply-chain
  AISecurityLabs.orgUpdated 5 Oct 20268 min read

• Security for Cursor Development

  Cursor's agent runs commands with your permissions. This post covers the risks, the incidents that turned configuration into code execution, their impact, and the settings, checks and habits that control them.

  cursorcoding-agentsprompt-injectionleast-privilegesandboxingsupply-chain
  AISecurityLabs.orgUpdated 6 Oct 20267 min read

• Security for Gemini Development

  Gemini CLI and Code Assist agent mode run commands with your permissions. This post covers the risks, the incidents, their impact, and the settings, checks and habits that control them.

  geminicoding-agentsprompt-injectionleast-privilegesandboxingsupply-chain
  AISecurityLabs.orgUpdated 6 Oct 20266 min read