Home / Resources

Roll out Claude Code without audit findings

Claude Code security depends on the permissions, sandbox and managed settings configured for each team.

Updated November 12, 2026

Claude Code security limits agents and reviews code

Claude Code security covers agent limits and code review. ZeroTB's software and team maintain post-audit SOC 2 controls for US software, AI, fintech and healthtech companies with 25 to 250 people.

  • Limit agent actions. Permission modes, the sandbox and managed settings determine what sessions can do

  • Review generated code. `/security-review`, the GitHub Action and Claude Code Security look for vulnerabilities

  • Control production changes. Branch protection and required reviews determine which changes reach production

Claude Code's safety depends on its permission mode

Claude Code uses Anthropic's security program, backed by a SOC 2 Type 2 report and ISO 27001 certificate. Permission modes govern actions without approval prompts.

Ask before actions. Manual mode starts read-only and asks before edits, tests or commands.

Classify automatic actions. Auto mode blocks actions its classifier judges unsafe, and organizations can disable it.

Retain deny rules. Ask and deny rules apply, and curl and wget are never auto-approved.

Claude Code permissions

The Bash sandbox covers shell commands only

The sandboxed Bash tool enforces filesystem and network isolation at operating-system level for shell commands and their child processes.

Check other routes. File tools, MCP servers and hooks run outside the Bash sandbox.

Distinguish prompt boundaries. The working-directory prompt allows approved commands wherever the user has write permission.

Isolate cloud sessions. Each cloud session has an Anthropic-managed VM that never receives GitHub credentials.

Claude Code sandboxing

Untrusted repositories and MCP servers carry the risk

Claude Code reads repository content and tool responses that can contain prompt injection. MCP servers also need review: Anthropic security-audits none of them.

Inspect trust prompts. Unfamiliar folders and project MCP servers require approval, which `-p` sessions skip.

Review plugin contents. Plugins add skills, hooks and MCP servers beyond those listed in `.mcp.json`.

Isolate unfamiliar code. A VM or dev container with restricted credentials limits access around untrusted repositories.

Claude Code data follows your account's terms

Claude Code's Team, Enterprise and API accounts use Commercial Terms. Free, Pro and Max use Consumer Terms, where users set training preferences.

Choose company accounts. Run company work through a Team, Enterprise or API account under Anthropic's terms.

Restrict sensitive files. Credentials and logs beside the task need access restrictions.

Store credentials securely. API keys and tokens use the macOS Keychain when available.

Managed settings enforce Claude Code enterprise security

Claude Code enterprise security relies on managed settings taking precedence over developers' configurations. An administrator can enforce the organization's standard across the team.

Share approved permissions. Version-controlled permission files distribute approved settings across the team.

Restrict MCP servers. Managed MCP configuration limits which servers can run.

Audit settings changes. OpenTelemetry metrics track usage, and ConfigChange hooks audit settings edits.

Anthropic's security review and scanner find code flaws

Claude Code security review examines current-branch changes through `/security-review`. The GitHub Action puts its findings on pull requests for developers to review.

Review trusted requests. The GitHub Action is intended for trusted pull requests and lacks prompt-injection hardening.

Inspect codebase findings. Claude Code Security reasons about code and suggests patches for human review.

Guide session reviews. The security guidance plugin asks Claude to review and fix its own changes.

Claude Code Security's limited Team and Enterprise research preview reasons beyond static rules and leaves patch application to developers.

A clean security review leaves branch rules unchecked

A Claude Code security review judges code. SOC 2 change management also needs branch protection and required reviews to hold on every repository.

Enforce GitHub rules. GitHub applies branch protection to cloud-session pushes through the connected access.

Inspect bypass permissions. A rule the connected access can bypass cannot block that session's push.

Catch later drift. New repositories can lack protection, and restored review rules can be removed again.

ZeroTB checks and restores controls Claude Code changes

ZeroTB carries failed SOC 2 controls through repair and verification. Daily checks read GitHub and other changed systems without a connection to Claude Code.

Start with observation. Access starts read-only, with revocable write grants scoped to each action class.

Review repair requests. Your team reviews and merges repairs, and AI cannot mark a control healthy.

Detect recurring gaps. The next check catches a review rule removed after restoration.

Change and development controls

Settings, security reviews and ZeroTB cover different gaps

Claude Code settings restrict sessions. Security reviews inspect code, branch protection controls merges, and ZeroTB takes responsibility for repairing failed SOC 2 controls.

TaskClaude Code settingsSecurity review toolsBranch protectionZeroTB
What it controlsWhat a session may run and reachVulnerabilities in changed codeWhich pushes and merges GitHub acceptsSOC 2 commitments, checked daily
What it leaves openWhich changes reach productionWhether required reviews still applyRules the connected access can bypassCode vulnerabilities remain with security review tools
Who acts on a gapYour admins, through managed settingsThe developer, finding by findingThe repository ownerZeroTB prepares repairs, your team approves
What the auditor seesLogs of every cloud-session operationGitHub Action findings on the pull requestCurrent rule without its repair historyA signed Verified Control Record

Example of restoring required review

This example shows a branch after required review disappears. The Verified Control Record connects its requirement and failed condition with the change, approval and result.

Block changes without required review
A required review commitment: one reviewer required, required approvals observed at zero, the owner's approved restoration to one, and a dated test blocking a merge without approval.
  1. Required review. The approved rule requires another person's review before production changes.

  2. Missing restriction. The branch setting has fallen to zero required approvals.

  3. Approved correction. The repository owner authorizes restoring one required review.

  4. Verified result. A dated test shows that the restored rule blocks an unapproved change.

Set five controls before rolling out Claude Code

Map the commitment

Identify the SOC 2 requirement, its systems and its owner.

Set permission modes

Choose Manual or auto mode and define deny rules.

Sandbox shell commands

Turn on filesystem and network isolation for shell commands.

Vet MCP servers

Approve servers and plugins, then restrict them through managed settings.

Verify and record

Test branch rules after repairs and retain the results.

Sources

  1. Anthropic, Security, 2026.
  2. Anthropic, Permissions, 2026.
  3. Anthropic, Sandboxing, 2026.
  4. Anthropic, Data usage and Plugins overview, 2026.
  5. Anthropic, Automated security reviews in Claude Code and Use Claude Security, 2026.
  6. Anthropic, Claude Code Security, 2026.
  7. Anthropic, Security review GitHub Action, 2026.

Start with the Pilot

The eight-week Pilot maps up to 25 commitments and takes two real control gaps through verified restoration around agent-assisted development.