Token导航 LogoToken导航TokenDH.com
开发操作浏览器github未标认证来源可访问许可证需确认审计通过

bitwarden-security-context位管理员安全上下文

Agent Skill

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

总安装

489

周安装

21

GitHub Stars

84

下载量

171
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:bitwarden-security-context(位管理员安全上下文)
来源仓库:https://github.com/bitwarden/ai-plugins
仓库路径:skills/bitwarden-security-context
安装命令:
npx skills add https://github.com/bitwarden/ai-plugins --skill bitwarden-security-context
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/bitwarden/ai-plugins --skill bitwarden-security-context

简介

bitwarden-security-context 用于辅助安全审计、权限检查和常见漏洞排查,提供 Bitwarden 安全框架参考。

  • 它支持敏感配置梳理、依赖风险分析和鉴权逻辑审查,但不能替代完整安全工具输出。
  • 通过 npx skills add 命令安装,需结合项目安全需求使用。
  • 涉及密钥、令牌或生产系统时,应先确认最小权限、脱敏方式和操作边界。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

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

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.43%
按下载量换算62

Claude

29.91%
按下载量换算51

Cursor

19.75%
按下载量换算34

Gemini CLI

9.54%
按下载量换算16

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills