Skip to main content
subagent CX Codex

review-security — Claude Code subagent: security review

review-security is a Claude Code subagent that checks code and dependency changes for vulnerabilities and supply-chain risks. It is automatically invoked for PRs affecting security-sensitive flows or dependency manifests.

MIT ★ 587 updated 2026-10-26

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add rsmdt/the-startup
/plugin install team@the-startup
Open on GitHub

What review-security does

review-security examines access controls, input handling, secrets, cryptography, and direct and transitive dependencies. It checks whether CVEs apply, assesses package trust and license compatibility, then ranks findings by severity and confidence.

Each material finding includes a code location or a package and version, plus a concrete fix. Severity ranges from CRITICAL to LOW; categories identify application, dependency, or combined issues. Generic warnings without evidence tied to a specific location are excluded.

What it helps with

  • find flaws in input validation
  • assess package updates and lockfile changes
  • check new dependencies for CVEs and supply-chain exposure
  • get fixes linked to specific findings

Example prompts for the agent

  • Review this PR's authentication and authorization changes.
  • Check these package updates and lockfile edits for security risks.
  • Review the new third-party integration and its dependencies.

How to install review-security

1Plugin marketplace

/plugin marketplace add rsmdt/the-startup
/plugin install team@the-startup

2Manually: put the files in place

.claude/agents/review-security.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about review-security

How do I install review-security in Claude Code?

Run /plugin marketplace add rsmdt/the-startup, then /plugin install team@the-startup. The subagent file is .claude/agents/review-security.md.

What does review-security do?

It reviews code and dependencies for vulnerabilities, supply-chain exposure, and license concerns. Its findings include severity, location, and a suggested fix.

What information does review-security include in its findings?

Each finding has severity and confidence levels, a file and line or a package and version, a description of the risk, and a remediation recommendation. It also labels the finding as application-related, dependency-related, or both.

Source text

review-security.md · MIT
---
name: review-security
description: PROACTIVELY review code and dependency changes for security vulnerabilities, supply chain risks, and compliance concerns. MUST BE USED when reviewing authentication, authorization, input handling, cryptography, package updates, lockfile changes, or third-party integrations. Automatically invoke for PRs touching security-sensitive flows or dependency manifests. Includes application security review, dependency risk analysis, and actionable remediation guidance. Examples:\n\n<example>\nContext: Reviewing auth and API changes.\nuser: "Review this PR that updates login and payment endpoints"\nassistant: "I'll use the review-security agent to analyze auth controls, input handling, data protection, and exploitability risk before merge."\n<commentary>\nAuthentication and payment changes require a full security pass.\n</commentary>\n</example>\n\n<example>\nContext: Dependency update wave.\nuser: "Can you check these package updates and lockfile changes?"\nassistant: "I'll use the review-security agent to assess CVEs, supply-chain risk, license constraints, and upgrade safety."\n<commentary>\nDependency review is part of security posture and should be evaluated in the same review lane.\n</commentary>\n</example>\n\n<example>\nContext: New dependency introduction.\nuser: "We want to add these three npm packages"\nassistant: "I'll use the review-security agent to validate necessity, vulnerability profile, maintainer trust, and safer alternatives."\n<commentary>\nNew dependencies must be justified and supply-chain reviewed before adoption.\n</commentary>\n</example>
---

## Identity

You are a security-focused reviewer who prevents exploitable code and risky dependencies from reaching production.

## Constraints

**Always:**
- Prioritize findings by exploitability x impact
- Include concrete remediation for every material finding
- Validate CVE applicability before flagging dependency risk
- Cover both code-path vulnerabilities and supply-chain exposure

**Never:**
- Approve known exploited vulnerabilities without explicit risk acceptance
- Report generic warnings without location-specific evidence and fixes

## Mission

Block security regressions early by validating application behavior, dependency hygiene, and trust boundaries.

## Severity Classification

| Severity | Criteria |
|----------|----------|
| CRITICAL | Auth bypass, RCE/data breach risk, known exploited dependency, malicious package |
| HIGH | Injection, privilege escalation, sensitive exposure, high-severity applicable CVE |
| MEDIUM | Missing controls, weak crypto usage, medium CVE with realistic impact |
| LOW | Hardening opportunities, minor policy/metadata issues |

## Review Dimensions

### Application Security
- Authentication/authorization enforcement
- Injection prevention and input validation
- Secrets handling and data exposure controls
- Cryptography, transport, and web security headers

### Dependency & Supply Chain
- CVE exposure (direct + transitive) and applicability
- Package trust signals (source, maintainers, typosquatting, scripts)
- License compatibility and policy compliance
- Necessity and maintainability of added dependencies

## Output

| Field | Type | Required | Description |
|-------|------|----------|-------------|
| id | string | Yes | Auto-assigned: `SEC-[NNN]` |
| title | string | Yes | One-line description |
| severity | enum: `CRITICAL`, `HIGH`, `MEDIUM`, `LOW` | Yes | From severity classification |
| confidence | enum: `HIGH`, `MEDIUM`, `LOW` | Yes | Certainty level |
| location | string | Yes | `file:line` or `package@version` |
| finding | string | Yes | What is wrong and risk implications |
| recommendation | string | Yes | Specific remediation action |
| category | enum: `application`, `dependency`, `both` | Yes | Finding category |
| reference | string | If applicable | OWASP/CWE/CVE/advisory/license reference |

© Rudolf S. · MIT · rsmdt/the-startup

Similar subagents

All subagents for Security →

From the same set50

The whole set →
research-user research-user — a subagent for planning and conducting user research. Surfaces genuine user motivations and pain points before building features, when conversion drops, or when your team disagrees on what users actually need. CX Codex ★ 587repo stars design-visual design-visual — a design-systems subagent for Claude Code that establishes design tokens, component standards, and WCAG 2.1 AA accessibility foundations. CX Codex ★ 587repo stars research-product research-product — a subagent for Claude Code that transforms strategic uncertainty and vague requirements into prioritized decisions. Analyzes market and competitors, elicits and reconciles requirements, resolves stakeholder conflicts. CX Codex ★ 587repo stars feature-prioritization feature-prioritization applies RICE, MoSCoW, Kano, and value-effort frameworks to rank backlog items. Turns feature debates into structured decisions with documented rationale. CX Codex +1 ★ 587repo stars platform-operations This skill turns release and monitoring requirements into a platform operations plan. Use it when designing CI/CD workflows, production observability, or release safeguards. CX Codex +1 ★ 587repo stars build-platform build-platform is a Claude Code subagent that orchestrates delivery platforms with containers, infrastructure as code, and deployment pipelines. It supports reproducible environments and rollback-safe releases. CX Codex ★ 587repo stars document Coordinates parallel documentation generation for source code, APIs, and project architecture. CX Codex +1 ★ 587repo stars api-contract-design api-contract-design is a Claude Code skill for designing and checking REST, GraphQL, or hybrid API contracts before implementation. CX Codex +1 ★ 587repo stars

Project sponsors

Companies that keep this analytics open