Claude Code security review

What it does

Anthropic documents automated security reviews in Claude Code. Developers can run /security-review in the terminal to analyse pending changes; a GitHub Action (anthropics/claude-code-security-review) can review pull requests and post comments. Anthropic’s help centre and blog list checks for common patterns including SQL injection, XSS, authentication/authorisation flaws, insecure data handling and dependency vulnerabilities (vendor-claimed coverage). The GitHub Action repository states it is not hardened against prompt injection and should only review trusted PRs. Anthropic labels the features as a complement to, not a replacement for, existing security practices. Availability is described for Claude Code users on individual paid plans (Pro or Max) and API Console accounts.

Frameworks (vendor-stated)

No framework tags yet.

Government authorizations

Registry records checked 2026-10-18. Scope “listing” means the certified product is this listing or the government boundary it already documents; “platform-only” means another product line is certified and the vendor does not state this agent is inside that boundary.

Pricing (as published)

Included with Claude Code for users on individual paid plans (Pro or Max) and pay-as-you-go API Console accounts, per Anthropic’s help centre. Public Claude plan list prices are on claude.com/pricing; the GitHub Action uses a Claude API key.

India relevance

PR and local review of common vulnerability classes is relevant to secure-development programmes, including CERT-In-oriented handling. Anthropic does not market a CERT-In module.

Tasks

appsecpr reviewsastvulnerability management

Sources

1. support.claude.com/en/articles/11932705-automated-security-reviews-in-claude-code (primary)
2. claude.com/blog/automate-security-reviews-with-claude-code
3. github.com/anthropics/claude-code-security-review
4. anthropic.com/legal/privacy
5. dir.texas.gov/resource-library-item/tx-ramp-certified-cloud-products

Last verified 18 Oct 2026. Framework tags indicate relevance, not certification; “vendor-claimed” items are as marketed by the vendor. Spotted an error? Submit a correction or email [email protected]. See our methodology.

Use-case comparisons

• AI code security agents — 33 verified listings (Application security scanning, suggested or automated code fixes, and pull-request security review)

Compare Claude Code security review with

• 
  Aikido AI AutoFix vs Claude Code security review
• 
  AISLE (autonomous vulnerability discovery, triage and verified-fix agents) vs Claude Code security review
• 
  Amazon Q Developer security scanning vs Claude Code security review
• 
  Amnify security agents (agent-driven code audit, AI pentesting, PR review and autofix pull requests) vs Claude Code security review
• 
  Black Duck Signal (agentic AI AppSec) vs Claude Code security review
• 
  Checkmarx One Assist vs Claude Code security review
• 
  Claude Code security review vs Codacy AI Reviewer
• 
  Claude Code security review vs Contrast AI SmartFix (agentic vulnerability remediation)
• 
  Claude Code security review vs Cursor Bugbot
• 
  Claude Code security review vs CybeDefend Cybe AutoFix (AI code security agent that opens tested fix pull requests)

Alternatives

• 
  Aikido AI AutoFix — Aikido AutoFix turns SAST, SCA, IaC, container, pentest and AI code-audit findings into reviewable pull requests or IDE patches. Vendor is Belgium-founded with a Ghent European HQ.
• 
  AISLE (autonomous vulnerability discovery, triage and verified-fix agents) — Prague-headquartered AI code-security platform in which thousands of agents analyse a codebase in parallel for exploitable vulnerabilities, fix agents write patches, and agentic verification builds the repo and runs tests before opening a pull request for human merge. October 2026 added agent-driven proof of exploitability against running web apps and APIs. Cohere signed a letter of intent to acquire AISLE on Oct 15, 2026.
• 
  Amazon Q Developer security scanning — Amazon Q Developer code reviews that scan for SAST issues, secrets, IaC misconfigurations, quality issues, deployment risks and SCA, with some in-IDE suggested fixes.
• 
  Amnify security agents (agent-driven code audit, AI pentesting, PR review and autofix pull requests) — German AppSec product from Düsseldorf: a team of agents audits repositories (SAST, secrets, SCA, IaC, CI/CD) and cloud accounts, triages signals so only confirmed findings surface, pentests running apps inside a verified scope with a separate agent reproducing every finding, reviews pull requests with a merge-blocking status check, and opens fix pull requests that run your tests but never merge themselves.
• 
  Black Duck Signal (agentic AI AppSec) — Agentic AI application security tool (GA March 2026) with role- and task-based agents that analyse new code in any language, filter findings by exploitability and apply verified fixes, callable from Claude Code, Gemini and GitHub Copilot via MCP.
• 
  Checkmarx One Assist — Family of agentic AppSec agents on Checkmarx One (Developer Assist in the IDE, plus triage/remediation). Checkmarx Ltd’s registered office is Ramat Gan, Israel.

See all Claude Code security review alternatives →

FAQ (from this dataset)

What does Claude Code security review do?

Anthropic automated security review in Claude Code: the /security-review command and the anthropics/claude-code-security-review GitHub Action for pull-request comments.

How much does Claude Code security review cost?

Included with Claude Code for users on individual paid plans (Pro or Max) and pay-as-you-go API Console accounts, per Anthropic’s help centre. Public Claude plan list prices are on claude.com/pricing; the GitHub Action uses a Claude API key.

Where is Anthropic headquartered?

United States

What are alternatives to Claude Code security review?

See the Claude Code security review alternatives page for category-sharing listings in relevance order, not a ranking. Claude Code security review alternatives.

Stay updated