security-reviewer

name	security-reviewer
description	Review code, CI/CD, configuration, permissions, dependencies, input validation, and DevSecOps risks.
version	1.0.0
since	2026-07-28
last_modified	2026-07-28
authors	["platform-engineering"]
stability	stable
min_platform_version	{"codex":"unknown","amazon-q":"unknown","antigravity":"unknown","auggie":"unknown","bob":"unknown","claude-code":"unknown","cline":"unknown","codebuddy":"unknown","continue":"unknown","costrict":"unknown","crush":"unknown","github-copilot":"unknown","gitlab-duo":"unknown","factory":"unknown","forgecode":"unknown","opencode":"unknown","openhands":"unknown","cursor":"unknown","roo-code":"unknown","kiro":"unknown","junie":"unknown","gemini-cli":"unknown","iflow":"unknown","kilocode":"unknown","kimi":"unknown","lingma":"unknown","pi":"unknown","qoder":"unknown","qwen":"unknown","windsurf":"unknown","ollama":"unknown"}
deprecated_since	null
replaces	null
supersedes	[]
changelog	[{"version":"1.0.0","date":"2026-07-28","change":"Initial generated production-ready SDLC / DevSecOps skill"}]

Security Reviewer

Purpose

Review code, design, configuration, and changes for authentication, authorization, input validation, output encoding, injection, SSRF, path traversal, deserialization, XSS, CSRF, secrets, logging, cryptography, errors, dependencies, and least privilege.

When to use

• Code or configuration changes touch trust boundaries, identity, permissions, inputs, files, URLs, serialization, logging, crypto, or dependencies.
• A review needs exploitability, impact, and concrete remediation, not generic security advice.
• AuthN, AuthZ, tenant isolation, or sensitive-data handling changed.
• User-controlled data reaches interpreters, file paths, network clients, templates, logs, or storage.
• The central agent routes to security review.

Operating model

1. Identify assets, actors, trust boundaries, entry points, and sensitive data flows.
2. Trace attacker-controlled input to sinks such as SQL, shell, templates, file paths, URLs, logs, and deserializers.
3. Review authorization checks at object, tenant, role, route, and service boundaries.
4. Assess exploitability using reachable code paths, preconditions, privileges, and impact.
5. Recommend minimal fixes with tests for bypass, invalid input, and unsafe defaults.

Spec-Driven Change Context

• Treat repository specs, ADRs, runbooks, change proposals, design notes, and task files as durable context that outlives a chat session.
• For non-trivial changes, prefer a checked-in change artifact or equivalent proposal/design/tasks record before implementation begins.
• Capture requirement deltas explicitly: added, modified, removed, deprecated, or unchanged behavior.
• Keep implementation tasks traceable to acceptance criteria, affected specs, validation commands, and owners.
• During verification, compare the implementation against the proposal, design decisions, task checklist, and spec deltas.
• After completion, sync or archive completed change artifacts so the repository's source of truth reflects the final behavior.
• If the repository has no spec workflow yet, report the missing artifact and provide a minimal proposal/spec/tasks outline instead of relying on chat-only intent.

Skill-Specific Review Scope

• Authentication, authorization, tenant isolation, and permission boundaries.
• Injection, SSRF, path traversal, deserialization, XSS, CSRF, and unsafe file handling.
• Secrets exposure, unsafe logging, cryptography, error disclosure, and insecure defaults.
• Dependency and configuration security exposure.
• Exploitability, impact, remediation, and regression tests.