TL;DR: Copilot Chat can inherit Bypass Approvals from a workspace-scoped setting, according to Repello AI, when a repository changes .vscode/settings.json. Workspace trust decisions now govern assistant actions as well as code loading, so approval mode needs separate policy control.
Editorial analysis by NHI Mgmt Group, based on content published by Repello AI: “Workspace Trust Is Not AI Consent: A VS Code Copilot Bypass-Mode Case Study”.
Key questions
Q: Why does workspace trust increase risk for AI assistants in developer tools?
A: Because the same trust decision can now enable model-driven actions that were never part of the original code-trust mental model.
Q: How should teams stop malicious repositories from altering AI approval settings?
A: Treat assistant approval mode as a centrally governed control, not a developer preference.
Q: What breaks when a repository can change Copilot approval mode at load time?
A: The failure is that repository trust becomes a permission grant for tool execution, not just code loading.
Practitioner guidance
- Inspect workspace settings before granting trust Review .vscode/settings.json for chat.permissions.default, chat.tools.autoApprove and other assistant-related settings before opening an unfamiliar repository in trusted mode.
- Open untrusted code in restricted mode first Use VS Code Restricted Mode for initial review so agent tools, tasks and extensions stay disabled until the repository has been examined.
- Force enterprise-level approval policy Set central policy so new sessions fall back to Default Approvals even when a workspace requests a more permissive mode.
Bottom line: A repository can change VS Code Copilot Chat into a permissive execution mode through workspace-scoped settings, which means workspace trust now affects agent behaviour as well as code loading.
Glossary terms: Workspace Trust, Bypass Approvals, Workspace-scoped Setting, Agentic Tool Execution
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
Workspace trust has become an AI authorisation boundary: The industry still treats the trust prompt as a code-execution decision, but agentic tools make it a permission decision for model-driven actions as well. That is a different governance problem because the user is no longer authorising only the repository’s code path. The implication is that workspace trust, AI action approval, and developer workstation policy can no longer be managed as one undifferentiated control.
A few things that frame the scale:
- 24,008 unique secrets were exposed in MCP configuration files in 2025 alone, the protocol's first year of widespread adoption, according to the State of Secrets Sprawl 2026.
A question worth separating out:
Q: What is the difference between trusting a workspace and trusting an AI agent?
A: Trusting a workspace is a code-execution decision about files, tasks and extensions. Trusting an AI agent is a separate decision about whether the assistant may act autonomously with tools, so the two should not be collapsed into one prompt or one policy boundary.
👉 Read our full editorial: Workspace trust now governs agent autonomy in VS Code Copilot