# Claude Code Security: Run the Agent Safely on Enterprise Code | Alher Tech

> The exact security posture Alher Tech deploys for regulated B2B clients using Claude Code: least privilege, PreToolUse gates, audit trails and EU/US data residency.

- Canonical page: https://alhertech.com/en/claude-code/enterprise-security/
- Site: Alher Tech (custom software, AI agents and SEO engineering, https://alhertech.com/)
- Contact: https://alhertech.com/en/contact/

---

Large enterprises need more than "looks fine". They need auditable guardrails, sandboxing, secret protection and a clean story for their CISO. Below is the exact security posture we deploy for regulated B2B clients.

Updated: April 24, 2026

## Principle: least privilege

The agent runs as an OS user with access only to the repo. No database creds in `.env`; instead, short-lived tokens issued by the MCP server. No AWS or GCP creds on the box; use IAM roles on ephemeral CI runners.

## PreToolUse gates

Deny-list on paths (`.env*`, `**/secrets/**`, `infra/**/production/**`). Require explicit confirmation for Bash commands that contain `rm`, `curl` to untrusted domains, or database mutations. Block outbound network except on an allowlist.

## Audit trail

Every session transcript is archived to an S3 bucket with 7-year retention, keyed by engineer and client. PR metadata links back to the transcript. A CISO can reconstruct any change end-to-end.

## Data residency

For EU customers we deploy Opus 4.7 via Amazon Bedrock in eu-central-1 or Google Vertex AI in europe-west4. For US federal we use Bedrock GovCloud. The Claude Code CLI is configured to talk to the regional endpoint, not the public Anthropic API.

## Frequently asked questions

### Can Claude Code access production?

Only via MCP servers that you explicitly configure. By default the agent has no production credentials. We recommend keeping that default.