… Latest Safeguarding VS Code against prompt injections When a chat conversation is poisoned by indirect prompt injection, it can result in the exposure of GitHub tokens, confidential files, or even the execution of arbitrary code without the user’s explicit consent. …
… Model selection You can now choose which AI model Copilot coding agent uses for your task, directly from Jira. Simply indicate the model you wish to use in your comment when mentioning @GitHub Copilot . For more information on available models, see Supported AI models in Copilot . …
… This means you can use the models and providers you’re already paying for, operate in air-gapped environments, and maintain direct control over your LLM spend, all while keeping the same agentic terminal experience. …