
bitwarden-security-engineer
Application security engineering plugin that triages findings, threat models, and reviews code for vulnerabilities.
- version
- 2.1.0
- GitHub stars
- 165
What it does
- Adds the
bitwarden-security-engineeragent plus skills for code security, secrets, dependencies, threat modeling, and architecture review - Covers triage of Aikido and Dependabot alerts via
triaging-security-findings, with severity mapping and a false positive protocol - Runs
perform-security-reviewas a multi-agent review using two-axis Severity × Confidence scoring across chat, file, or CI output - Designed for Bitwarden engineers who need reviews aligned to internal principles and to the Aikido plugin, which must be installed first
Application security engineering assistant for vulnerability triage, threat modeling, and secure code analysis.
Add marketplace
/plugin marketplace add bitwarden/ai-pluginsRun it inside Claude Code once, then install the plugin below.
Install
/plugin install bitwarden-security-engineer@bitwarden-marketplaceRun it inside Claude Code after adding the marketplace.
Files
Discovered from sourceSecurity Review Workflow
Follow these steps when conducting a manual security code review:
- Identify the attack surface. Determine entry points: API endpoints, message handlers, file parsers, user-facing forms. Read route definitions and controller registrations to build a map.
- Trace data flows from sources to sinks. Follow untrusted input (HTTP parameters, headers, request bodies, file uploads, external API responses) through all transformations to dangerous operations (database queries, command execution, HTML rendering, file system access).
- Check trust boundary crossings. At every point where data crosses a trust boundary (client→server, service→service, user input→database), verify that validation, authentication, and authorization are enforced.
- Apply framework checklists. Consult
references/framework-checklists.mdfor OWASP Web/API/Mobile Top 10 and CWE Top 25. Check each applicable category against the code under review. - Adopt an adversarial mindset. Form a hypothesis (e.g., "I can bypass SSO", "I can access another user's vault") and work backwards to determine what conditions would make it exploitable.
- Map findings to CWE IDs. Every finding must include the specific CWE identifier, the code location, and the data flow that makes it exploitable.
- Classify by practical exploitability. Distinguish between practically exploitable vulnerabilities and theoretical risks. Prioritize accordingly but document both.
Key Vulnerability Categories
The most frequently encountered categories across Bitwarden's stack:
- Injection (CWE-89, CWE-78, CWE-77) — Unsanitized input reaching SQL queries, OS commands, or LDAP queries. Always use parameterized queries and avoid string concatenation.
- Broken Access Control (CWE-862, CWE-287, CWE-306) — Missing authorization checks, IDOR, privilege escalation. Verify per-object ownership checks and role enforcement at every layer.
- XSS (CWE-79) — User input rendered in HTML without encoding. In Angular, avoid
innerHTMLandbypassSecurityTrust*with untrusted content. - SSRF (CWE-918) — User-controlled URLs in server-side requests. Validate against host allowlists.
- Insecure Deserialization (CWE-502) — Type-handling enabled on untrusted input. Avoid
TypeNameHandling.Allin JSON.NET. - Path Traversal (CWE-22) — User-supplied paths reaching file system operations. Canonicalize and validate against a base directory.
- Cryptographic Failures — Weak algorithms, hardcoded keys, predictable IVs. See the
reviewing-security-architectureskill for approved algorithms.
For complete framework checklists (all OWASP and CWE categories), consult references/framework-checklists.md.
For CORRECT/WRONG code examples in C#, TypeScript, and SQL, consult references/vulnerability-patterns.md.
Adversarial Review Mindset
Adopt an adversarial mindset during security code review — this differs from regular code review which seeks to strengthen code.
How to think adversarially:
- Create a hypothesis — e.g., "I can bypass SSO", "I can access another user's vault", "I can escalate from member to admin"
- Work backwards — What conditions would need to be true for the attack to succeed? Can those conditions be fabricated?
- Question assumptions — Is that authorization check always reached? What happens if the middleware fails? What if the token is malformed but not invalid?
- Consider failure modes — What happens when things fail? Do they fail open (insecure) or fail closed (secure)?
Critical Rules
- Authentication before authorization. Always verify the user is who they claim to be before checking what they're allowed to do. Never skip auth checks in "internal" endpoints.
- Validate at trust boundaries. Every point where data crosses a trust boundary (client→server, service→service, user input→database) must validate. Never trust client-side validation alone.
- Map findings to CWE IDs. Every finding must include a specific CWE identifier with evidence: the code location and the data flow that makes it exploitable.
- Practical over theoretical. Distinguish between vulnerabilities that are practically exploitable in this system vs. theoretical risks. Prioritize accordingly but document both.
- Check the whole chain. A vulnerability isn't just the sink — trace from the source (user input) through all transformations to the sink (dangerous operation). If the chain is broken by sanitization, it's not exploitable.
Additional Resources
Reference Files
For detailed checklists and code examples, consult:
references/framework-checklists.md— OWASP Web Top 10, API Top 10, Mobile Top 10 (2024), CWE Top 25 lookup tablesreferences/vulnerability-patterns.md— CORRECT/WRONG code examples for C#/.NET, TypeScript/Angular, and SQL
Readme
Bitwarden Security Engineer Plugin
Claude Code skills for application security at Bitwarden. Generic AI coding assistance doesn't know our scanner toolchain, triage workflows, or threat modeling practices. These skills keep Claude focused on how we secure software here.
Overview
This plugin provides specialized skills for security engineering tasks — from triaging scanner findings and threat modeling to conducting multi-agent security code reviews. Skills can be invoked individually or orchestrated together for comprehensive coverage across code, dependencies, secrets, and architecture.
Prerequisites
triaging-security-findings, reviewing-dependencies, and perform-security-review query the Aikido feed via the aikido:issues skill. That skill ships in the separate aikido plugin — Aikido Security's own Claude Code plugin — and requires an authenticated MCP session. Install it with /plugin install aikido@claude-plugins-official and run /aikido:setup before using those skills. For triaging-security-findings and reviewing-dependencies, Aikido is the primary data source: if it isn't installed, these skills stop and ask you to install it rather than silently returning no findings. perform-security-review treats Aikido SAST/IaC/SCA/container evidence as one of several best-effort corroborating sources rather than a hard requirement — if it's unavailable, the review continues using whichever sources it could reach.
Skills
| Skill | What It Does |
|---|---|
triaging-security-findings | Triage Aikido feed findings (SAST, IaC, SCA, secrets, cloud, container, malware, EOL, license) via Jira, plus GitHub Dependabot and secret scanning alerts. Includes severity mapping, group-scope verification, false positive protocol, and fix patterns. |
threat-modeling | Generate security definitions, data flow diagrams, and threat catalogs using STRIDE. Follows Bitwarden's 4-phase AppSec engagement model. |
analyzing-code-security | Security code review against OWASP Web/API/Mobile Top 10, CWE Top 25. Step-by-step review workflow with adversarial mindset guidance. |
reviewing-dependencies | Dependabot triage, Aikido open-source and container scanning, transitive dependency risk analysis. NuGet and npm platform-specific guidance. |
detecting-secrets | Hardcoded credential detection with context-aware analysis. GitHub secret scanning integration, Azure Key Vault remediation. |
reviewing-security-architecture | Architecture-level review for authentication, authorization, encryption, trust boundaries, and cryptographic patterns. |
perform-security-review | Multi-agent security code review with 4 specialized agents, two-axis Severity × Confidence scoring, Aikido SAST/IaC/SCA/container evidence plus secret scanning and Dependabot evidence (the latter two are interactive only — not pre-approved, so CI records them as not checked), --base-ref <ref> to pick the comparison base, and flexible output (chat, file, or GitHub Actions). |
auditing-external-claude-plugins | Security audit of a third-party Claude Code plugin before it's vendored, covering MCP config, dependency supply chain, tool permission scope, and prompt-injection surface. Runs as an isolated subagent and writes a report file. |
Usage
Install the plugin, then ask for what you want in natural language. Example prompts:
Use the bitwarden-security-engineer:bitwarden-security-engineer agent to triage the open Aikido findings on this PR.
Use the bitwarden-security-engineer:bitwarden-security-engineer agent to create a threat model for the new Send feature.
Use the bitwarden-security-engineer:bitwarden-security-engineer agent to review this code for OWASP Top 10 vulnerabilities.
auditing-external-claude-plugins takes positional arguments instead:
/bitwarden-security-engineer:auditing-external-claude-plugins https://github.com/org/plugin <commit-sha>
References
External resources that informed each skill. Useful for maintainers updating skill content when upstream sources change.
threat-modeling
- Security Definitions — Official vocabulary and terminology
- Security Principles — P01-P06 foundation principles
- Security Requirements — VD/EK/AT/SC/TC requirement categories
- Threat Modeling Manifesto
- Threat Modeling Guide for Software Teams
- OWASP Threat Modeling Process
triaging-security-findings
analyzing-code-security
- OWASP Top Ten
- OWASP API Security Top 10
- OWASP Mobile Top 10 2024
- CWE Top 25 Most Dangerous Software Weaknesses
- OWASP Code Review Guide
reviewing-dependencies
- GitHub Dependabot Documentation
- Aikido Documentation
- OWASP Dependency-Check
- npm Security Best Practices
detecting-secrets
- GitHub Secret Scanning Documentation
- OWASP Secrets Management Cheat Sheet
- git-filter-repo Documentation
reviewing-security-architecture
Details
- Marketplace
- bitwarden/ai-plugins
- Source
- plugins/bitwarden-security-engineer
- Category
- Community
More from bitwarden/ai-plugins
All 25- bitwarden-shepherdv1.0.1
- bitwarden-software-engineerv1.1.0
- bitwarden-stripe-toolsv1.0.0
- bitwarden-tech-leadv3.1.0
- bitwarden-testing-toolsv1.5.1
- bitwarden-testmo-toolsv1.0.0
- claude-config-validatorv2.3.1
- claude-retrospectivev1.1.1
- atlassian-readerv1.2.1
- bitwarden-abacusv0.2.0
- bitwarden-abacus-toolsv1.3.0
- bitwarden-adr-toolsv1.0.0
- bitwarden-ai-telemetryv1.5.1
- bitwarden-atlassian-toolsv2.9.1
- bitwarden-code-reviewv3.1.0
- bitwarden-delivery-toolsv4.0.1
- bitwarden-design-toolsv0.1.0
- bitwarden-designerv0.1.0
- bitwarden-devops-engineerv0.3.1
- bitwarden-doc-parityv1.1.0
- bitwarden-initv1.2.2
- bitwarden-mailcatcher-toolsv1.0.0
- bitwarden-product-analystv0.1.7
- bitwarden-retrospective-toolsv1.2.0
Similar to bitwarden-security-engineer
More Security & Compliance
eccaffaan-m/everything-claude-code308.6K starsHarness-native ECC operator layer - 72 agents, 328 skills, 99 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready work
security-guidanceanthropics/claude-code156.1K starsSecurity review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injecti
ruflo-aidefenceruvnet/ruflo82.2K starsAI safety scanning, PII detection, prompt injection defense, and adaptive threat learning
front-end-checklistthedaviddias/Front-End-Checklist74.8K starsReview frontend code and live pages against 386 quality-gated rules for accessibility, performance, SEO, security, and HTML/CSS/JS best practices.
agentic-bundle-aas-privacy-compliance-engineeringsickn33/agentic-awesome-skills50.1K starsInstall the "AAS Privacy & Compliance Engineering" editorial skill bundle for Claude Code.
42crunch-api-security-testinganthropics/claude-plugins-official47.9K starsAutomate API security directly in Claude Code with 42Crunch - automatically audit OpenAPI specs, detect vulnerabilities aligned with OWASP API Security risks (i