AI Code Review Security: SOC 2, Data Privacy, and How Your Code Is Protected
How AI code review security works: SOC 2 Type II, encryption, access controls, no-training terms, and the data-privacy questions to ask before you connect an AI code reviewer to your GitHub repos.
Macroscope protects customer code with SOC 2 Type II audited controls, encryption at rest and in transit, privileged access limited to authorized users with a business need, and contract terms under which it does not train its own models on customer source code and requires its AI providers to agree not to train on that source code either.
AI code review security is the first question most engineering and security teams ask before connecting an AI code reviewer to their GitHub repositories, and it is the right question. An AI code review tool reads your source code, your pull requests, and your repository history. Before you grant that access, you should know where your code goes, who can see it, whether it is used to train models, and what compliance evidence the vendor can produce on request.
This guide covers how AI code review security works in practice, how Macroscope answers each question, where Macroscope's limits are, and a vendor-neutral checklist you can run against any AI code review tool.
Macroscope security at a glance
- Macroscope has SOC 2 Type II audit reports (2025 and 2026), available through a request-access workflow on the Macroscope Trust Center at trust.macroscope.com.
- Per its published controls, datastores holding sensitive customer data are encrypted at rest, and confidential data sent over public networks is encrypted in transit.
- Privileged access to production databases, systems, networks, and encryption keys is restricted to authorized users with a business need.
- Under Section 1.6.1 of its Terms, Macroscope does not use source code in customer content to train its own AI models (except as Section 4.1 provides), and it requires the AI providers it engages to agree not to train on that source code.
- Macroscope's subprocessors span cloud infrastructure, AI model and inference providers, web search, and business and operations tools. The trust center subprocessors page is the authoritative, current list.
- Macroscope's public pricing is usage-based and lists no separate security, compliance, or audit-report fee.
- Macroscope connects to GitHub through the Macroscope GitHub App, installed on the repositories you want to connect.
Is AI code review secure?
AI code review is secure when the vendor treats your source code as the sensitive asset it is, and Macroscope does that with SOC 2 Type II audited controls, encryption, restricted access, and contractual no-training terms for source code.
The risk with any AI code review tool is not the review itself. It is the data path. Your code travels from GitHub to the vendor's infrastructure, and from there to one or more large language model providers. Every hop is a place where code could be logged, exposed, or used for training. A secure AI code reviewer closes each of those gaps explicitly and can show you how.
The difference between a secure AI code reviewer and a risky one is not how capable the model is. It is whether the vendor can answer four questions without hedging. Are you SOC 2 compliant? Is my code encrypted, and who can access it? Do you or your model providers train on my code? Can I see the evidence? Macroscope answers all four publicly, through its trust center and its Terms.
What are the four pillars of AI code review security?
The four pillars of AI code review security are SOC 2 Type II, encryption, access control, and a no-training policy, and Macroscope publishes its position on all four.
They map directly to what a procurement or security review will ask about.
| Pillar | What it means | Macroscope's position |
|---|---|---|
| SOC 2 Type II | An independent auditor tested the vendor's security controls over a period of time | SOC 2 Type II reports (2025 and 2026) via request access on the trust center |
| Data encryption | Customer data encrypted in transit and at rest | Sensitive customer datastores encrypted at rest; confidential data encrypted over public networks |
| Access control | Only authorized staff can reach systems that hold customer code | Privileged access restricted to authorized users with a business need |
| No-training policy | Your source code is never used to train AI models | Terms §1.6.1: no training of Macroscope's models on customer source code (except as §4.1 provides); AI providers must agree not to train on it |
If an AI code review tool cannot speak clearly to all four, that is the signal to slow down.
What does SOC 2 Type II mean for AI code review?
SOC 2 Type II is the compliance attestation that matters most for AI code review, and Macroscope has SOC 2 Type II audit reports for 2025 and 2026.
SOC 2 is an independent audit against the Trust Services Criteria: security, availability, processing integrity, confidentiality, and privacy. A SOC 2 Type I report is a snapshot that shows the controls exist on a given day. A SOC 2 Type II report covers a window of time and tests whether those controls actually operated across that window. For a tool that reads your code on every pull request, Type II is the right bar, because you want evidence that the controls held up over months, not on the day of the audit.
Macroscope exposes its controls through a public trust center at trust.macroscope.com, with a request-access workflow for the audit reports. The public control categories are infrastructure, organizational, product, internal security procedures, and data and privacy. Examples include data retention procedures, deletion of customer data when customers leave, a data classification policy, unique production database authentication, restricted encryption key access, restricted production and firewall access, annual penetration testing, and a formal development lifecycle. The trust center also lists penetration test reports and security policies.
How does Macroscope encrypt your code and control access to it?
Macroscope encrypts datastores holding sensitive customer data at rest and encrypts confidential data in transit over public networks, and restricts privileged access to production systems to authorized users with a business need.
Encryption in transit protects code as it moves over public networks, for example between GitHub, the AI code review service, and model providers. Encryption at rest protects it where it is stored. Macroscope's published controls state both; if your review needs specific algorithms, ask through the trust center.
Access control is the part teams underestimate. In a multi-tenant system, the real questions are whether one customer's code can ever reach another customer's review, and which of the vendor's own staff can reach your source. Per the controls on Macroscope's trust center, privileged access to production databases, systems, networks, and encryption keys is restricted to authorized users with a business need, access is revoked on termination, and employees go through background checks and sign confidentiality agreements. Ask any vendor the same question: who can reach customer code, and under which audited controls.
Does AI code review train on your code?
Macroscope does not train its own models on customer source code, and it requires the AI providers it engages to agree not to train on that source code either.
This is the most important data-privacy question, because training is the one operation that absorbs your code into a system you do not control. Section 1.6.1 of Macroscope's Terms covers both halves:
- Macroscope does not train its models on your source code. Except as provided in Section 4.1, Macroscope will not use source code included in customer content to train its AI models. Section 4.1 covers other uses, including deidentified non-source-code content and an exception for the open-source partner program.
- AI providers agree not to train on it either. Customer content may be sent to third-party AI providers as part of the service, and Macroscope requires those providers to agree not to use the source code it provides on customers' behalf to train their AI tools.
These terms are about source code, not every kind of data. Provider data-retention terms vary; see each provider's entry on the subprocessors page rather than assuming zero retention.
The default behavior of many consumer AI products is different: data may be used to improve models unless you opt out. For an AI code review tool, the no-training commitment for source code should be the default and it should be contractual, not a setting you have to find.
Who are Macroscope's subprocessors?
Macroscope publishes its subprocessors, with each one's purpose and location, on the trust center subprocessors page, which is the authoritative, current list.
A subprocessor is any third party a vendor relies on to deliver the service: cloud hosting, model inference, messaging. If a vendor cannot give you this list, it cannot honestly answer where your code goes. Macroscope's list changes over time, so check the page rather than relying on a copy. Its main categories are:
| Category | Examples |
|---|---|
| Cloud infrastructure | Google Cloud Platform (primary hosting), plus AWS and Microsoft Azure |
| AI model and inference providers | For example OpenAI, Anthropic, Google Gemini (via Vertex), and inference platforms such as AWS Bedrock, Azure, Fireworks AI, Together, Baseten, and Modal |
| Web search | Parallel |
| Business and operations tools | Workflow infrastructure, payments, email delivery, analytics and error tracking, identity-provider integration, customer support, workflow automation, and internal collaboration |
Some entries list a future effective date, so check the page for current status. The trust center also says customers can choose to limit LLM data and inference to the US for some providers.
The trust center also discloses data that is explicitly not collected, including credit card information and personal health information. That kind of negative disclosure is what procurement teams look for.
What access does Macroscope need to your repositories?
Macroscope connects through the Macroscope GitHub App, which you install on the repositories you want to connect.
Macroscope's review reads each change and then explores the surrounding code in your repository to understand context beyond the diff. That is how it catches bugs across files, such as a function signature change in one file that breaks a caller in another. Source code sent to an AI provider is covered by the no-training terms above.
Because it is a GitHub App, you choose which repositories to connect, and Macroscope inherits permissions from GitHub. You then turn on review per repository in Settings. Many teams start with a single repository and expand once their security team is comfortable.
What security questions should you ask any AI code review vendor?
Ask every AI code review vendor the same ten questions, including Macroscope, and compare the answers side by side.
This checklist is vendor-neutral. A vendor that takes AI code review security seriously will have answers ready, and one that does not will hedge.
| Question to ask any AI code review vendor | What a strong answer looks like |
|---|---|
| Do you have a SOC 2 Type II report, and how do I get it? | Yes, with a trust center and a defined path to request the report |
| Is customer code encrypted in transit and at rest? | Yes, both |
| Who at the vendor can access customer source code? | Privileged access limited to authorized staff with a business need, under audited controls |
| Do you train any model on customer code? | No, stated in writing |
| Do your model providers train on customer code? | No, providers must agree not to by contract |
| Who are your subprocessors? | A named, public, current list |
| What data do you explicitly not collect? | A clear negative disclosure |
| What repository permissions does the integration request? | Scoped access you can limit to selected repositories |
| Which code hosts do you support, and how does the integration connect? | A direct answer you can verify |
| Is there a separate fee for security or audit documents? | No surprise security SKU |
For Macroscope, the answers are on the trust center, in the Terms, and on the pricing page: SOC 2 Type II reports, encryption at rest and in transit, privileged access restricted to authorized users with a business need, no training on customer source code by Macroscope or its AI providers under Terms §1.6.1, a public subprocessor list, GitHub through a GitHub App, and no separate security fee in the public pricing. Run CodeRabbit, Greptile, Cursor Bugbot, GitHub Copilot, or any other AI code review tool through the same table. Our CodeRabbit alternatives and Greptile alternatives guides cover the non-security differences.
Does Macroscope charge extra for security or compliance?
No, Macroscope's public pricing lists no separate fee for security, compliance, or audit documentation.
Macroscope's public pricing is fully usage-based: Code Review costs $0.05 per KB reviewed in the default Balanced detection mode, with a 10 KB minimum per review ($0.50 floor). There is no separate security, compliance, trust-center, or audit-report surcharge in the public pricing.
Audit reports are exposed through a request-access workflow on the trust center. Enterprise procurement teams can reach Macroscope at enterprise@macroscope.com, and the Enterprise plan on the pricing page lists custom MSA and DPA agreements and the SOC 2 Type II report. The no-training terms in Section 1.6.1 of the Terms apply to customers generally, not as an enterprise add-on.
How does AI code review security compare to human code review?
Human code review has its own security surface, and a governed AI code reviewer like Macroscope gives security teams one auditable data path instead of many unmanaged ones.
Every engineer with repository access can already read your source code, copy it, and paste it into external tools. The relevant comparison is not "AI versus no exposure." It is "a SOC 2 Type II vendor with a contractual no-training commitment for source code versus developers pasting code into consumer chatbots with no training guarantees and no audit trail."
In practice, a sanctioned AI code review tool can reduce the security surface: one contractually governed data path is easier to audit than dozens of ad hoc ones.
How do you get started with AI code review securely?
Start with Macroscope on one GitHub repository after your security team has reviewed the trust center.
Setting up AI code review on GitHub takes about five minutes:
- Review the trust center at trust.macroscope.com and request the SOC 2 Type II report if your process requires it.
- Install the GitHub App on a single repository first. Expand once your security team is comfortable.
- Confirm the no-training terms, access controls, and subprocessor list against your own data-handling requirements.
- Set spend controls. Cap spend per review or per PR (defaults are $10 per review and $50 per PR, adjustable), set monthly budget limits, and exclude files you do not want reviewed.
Frequently Asked Questions
Is Macroscope SOC 2 compliant?
Yes, Macroscope has SOC 2 Type II audit reports for 2025 and 2026. Its controls are published on the Macroscope Trust Center at trust.macroscope.com, and the audit reports are available through a request-access workflow. Type II means an independent auditor tested the controls over a period of time, not on a single day.
Does Macroscope train AI models on my code?
Not on your source code. Under Section 1.6.1 of its Terms, except as provided in Section 4.1, Macroscope will not use source code included in customer content to train its AI models, and it requires the AI providers it engages to agree not to use that source code to train their AI tools. Section 4.1 covers other uses, including deidentified non-source-code content and an exception for the open-source partner program.
Is AI code review safe for enterprise codebases?
Yes, AI code review is safe for enterprise codebases when the vendor is SOC 2 Type II, encrypts code in transit and at rest, restricts who can access it under audited controls, and contractually rules out training on your source code. Macroscope publishes its position on all four on its trust center and in its Terms.
Is AI code review secure?
Yes, when the vendor closes every gap in the data path between GitHub, its own infrastructure, and its model providers. Macroscope does this with SOC 2 Type II audited controls, encryption at rest and in transit, privileged access limited to authorized users with a business need, and no-training terms for source code that extend to its AI providers. Ask any vendor for evidence of each.
Can Macroscope employees see my code?
Access is restricted. Per the controls on the trust center, privileged access to production databases, systems, networks, and encryption keys is limited to authorized users with a business need. For specifics, ask through the trust center or contact@macroscope.com, and ask any AI code review vendor the same question.
Who are Macroscope's subprocessors?
Macroscope's subprocessors fall into cloud infrastructure (Google Cloud Platform as primary hosting, plus AWS and Microsoft Azure), AI model and inference providers (for example OpenAI, Anthropic, and Google Gemini via Vertex, plus inference platforms), web search, and business and operations tools. The authoritative, current list, with each subprocessor's purpose and location, is at trust.macroscope.com/subprocessors.
Does Macroscope charge extra for security or compliance documentation?
No, Macroscope's public pricing does not include a separate security, compliance, or audit-report fee. Pricing is usage-based, and audit reports are available through a request-access workflow on the trust center. Enterprise procurement can contact enterprise@macroscope.com.
What security questions should I ask an AI code review vendor?
Ask whether the vendor has a SOC 2 Type II report, whether code is encrypted in transit and at rest, whether employees can read customer code, whether the vendor or its model providers train on your code, who its subprocessors are, which code hosts and deployment models it supports, and whether audit evidence costs extra. Macroscope publishes its answers on its trust center and in its Terms, and a serious vendor will answer each one directly.