Bitwarden Security Context logo

Bitwarden Security Context

Organization
bitwarden
bitwarden-security-context

Bitwarden's security principles (P01-P06), security vocabulary, and data classification standards. Use when you need foundational security context for any Bitwarden development, review, or security task — such as understanding trust boundaries, data protection requirements, or Bitwarden-specific security terminology.

Overview

Publisherbitwarden
Repositoryai-plugins
Skill namebitwarden-security-context
Stars
149
Forks
19
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by bitwarden on GitHub. Read the source before you install it.

Installation

Install the Bitwarden Security Context AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/bitwarden/ai-plugins.git /tmp/ai-plugins
mkdir -p .claude/skills
cp -r /tmp/ai-plugins/plugins/bitwarden-security-engineer/skills/bitwarden-security-context .claude/skills/bitwarden-security-context
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bitwarden Security Context in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Bitwarden Security Context on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Bitwarden Security Context is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Bitwarden Security Context

Quick-reference for Bitwarden's foundational security framework. Use this for security context during development, code review, or security analysis without loading the full threat-modeling or architecture-review skills.

Security Principles (P01-P06)

These six principles form the foundation for all security decisions at Bitwarden.

PrincipleNameCore Guarantee
P01Servers are Zero KnowledgeBitwarden infrastructure cannot access unencrypted user data. The server must not enable weakening of user-chosen protections, masquerade server data as user-encrypted content, or access encrypted data outside the client context.
P02A Locked Vault is SecureHighly sensitive vault data cannot be accessed in plaintext once the vault is locked, even if the device is compromised after locking. Platform limitations (e.g., JS memory) are mitigated through buffer clearing and available security features.
P03Limited Security on Semi-Compromised DevicesFor unlocked vaults on devices with userspace malware (but intact OS/kernel), clients maximize kernel/OS-level protections and balance security with usability through controls like biometrics.
P04No Security on Fully Compromised SystemsBitwarden cannot guarantee vault protection when hardware or OS-level integrity is fully compromised. This applies to unlocked vaults only — locked vaults are covered by P02.
P05Controlled Access to Vault DataVault data, whether at rest or in use, is accessible only to authorized parties under the user's explicit control. Isolation mechanisms are critical in high-risk environments like web browsers.
P06Minimized Impact of Security BreachesLimit breach scope and duration through session invalidation, key rotation (countering "harvest now, decrypt later"), and post-compromise security (new data remains protected after a breach).

Controlled Exceptions

Principles have documented exceptions. Known examples:

  • P01 — Key Connector: Self-hosted SSO without passwords. The server holds encryption keys on behalf of the user.
  • P01 — Icons Service: Plaintext domain names are sent to retrieve favicons.

Full documentation: Security Principles

Security Vocabulary

Standard terminology for security discussions at Bitwarden.

TermDefinition
Vault DataA user's private information stored in Bitwarden (passwords, usernames, secure notes, credit cards, identities, attachments)
Protected DataData stored in unreadable format (typically encrypted) with expectations about secure key storage
Data at RestStored data not actively used or transmitted (disk storage on devices or servers)
Data in UseData actively being processed or accessed, held in volatile memory
Data in TransitData actively transferred between locations, processes, or devices
Secure ChannelA communication channel providing confidentiality (unreadable to unauthorized parties) and integrity (tamper-proof)
Trusted ChannelA secure channel that also provides authenticity (verified identities of communicating parties)
Data ExportingControlled process where data leaves Bitwarden unprotected, nullifying security guarantees. Requires informed consent.
Data SharingControlled data exchange within the Bitwarden secure environment (security guarantees maintained)
Data LeakingUnintentional departure of data from Bitwarden unprotected
Bitwarden Secure EnvironmentAny process or application adhering to Bitwarden's security standards

Full documentation: Security Definitions

Security Requirements by Category

CategoryScopeKey Obligations
VDVault DataProtected at rest (encrypted with UserKey), allowed in use (decrypted during unlock), trusted channels in transit, export requires informed consent
EKEncryption Keys256-bit security strength, protected at rest and in transit, must never be exported
ATAuthentication TokensProtected storage at rest, mandatory transit protection
SCSecure ChannelsConfidentiality, integrity, replay prevention, forward secrecy for long-lived channels
TCTrusted ChannelsSecure channel properties plus receiver identity verification

Full documentation: Security Requirements

Architecture Decision Records (ADRs)

Bitwarden's accepted architecture decisions are catalogued separately from the security principles above. See ${CLAUDE_PLUGIN_ROOT}/references/adr-alignment.md for how security assessments should check alignment against them.

Frequently asked questions

What does the Bitwarden Security Context AI skill do?

Bitwarden's security principles (P01-P06), security vocabulary, and data classification standards. Use when you need foundational security context for any Bitwarden development, review, or security task — such as understanding trust boundaries, data protection requirements, or Bitwarden-specific security terminology.

Why use Bitwarden Security Context on TypingMind?

Because you install it once and use it with any model. Bitwarden Security Context is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Bitwarden Security Context in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bitwarden/ai-plugins/tree/main/plugins/bitwarden-security-engineer/skills/bitwarden-security-context. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Bitwarden Security Context?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Bitwarden Security Context?

As many as you like. As long as a model supports skills, you can use Bitwarden Security Context with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Bitwarden Security Context AI skill free?

It is published on GitHub by bitwarden. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇