浏览器

password-auditor

试用

Audit password vault exports (Bitwarden, 1Password, KeePass, Chrome, Firefox) for reuse, weakness, staleness, breach exposure, and 2FA gaps without ever storing or transmitting a plaintext password. Use when the user asks to audit passwords, check password strength/reuse, review vault health, or verify whether credentials appeared in breaches.

它能做什么

Audit your password habits **without ever storing or transmitting a password**. Works from an exported CSV/JSON password vault (Bitwarden, 1Password, KeePass, Chrome, Firefox): it analyzes reuse, weakness, staleness, breach exposure, and 2FA availability, then produces an actionable prioritized fix…

技能文档

Password Auditor

Audit your password habits without ever storing or transmitting a password. Works from an exported CSV/JSON password vault (Bitwarden, 1Password, KeePass, Chrome, Firefox): it analyzes reuse, weakness, staleness, breach exposure, and 2FA availability, then produces an actionable prioritized fix list.

Overview

password-auditor ingests a vault export you already have on disk, computes risk findings locally (no network required except an optional breach check via the k-anonymity HaveIBeenPwned API, which only ever sees the first 5 hex chars of a SHA-1 hash), and emits:

  • A terminal risk report with a 0-100 security score
  • A prioritized remediation plan (worst offenders first)
  • Machine-readable JSON for tracking progress over time
  • A self-contained HTML dashboard you can open in any browser

When to Use

  • User says "audit my passwords", "are my passwords safe?", "how bad is my password reuse?"
  • After a vault export from any major password manager
  • Periodic security hygiene reviews (quarterly recommended)
  • Post-breach: check whether specific credentials appeared in known breaches
  • Before migrating between password managers (find weak/reused entries first)

Don't use for: storing passwords, auto-changing them, or managing a vault — this skill is read-only analysis. It never writes credentials anywhere and its output contains zero plaintext passwords.

How It Works

  1. Parse the export (auto-detects Bitwarden/1Password/KeePass/Chrome/Firefox CSV shapes, plus generic JSON).
  2. Normalize each entry: title, username, password, URL, last-modified date, folder/group.
  3. Analyze five risk dimensions:
    • Reuse — identical password across N entries (the #1 account-takeover multiplier)
    • Weakness — zxcvbn-style entropy estimation via length, charset, pattern, and common-password lists
    • Staleness — passwords untouched for years (pre-date modern breach knowledge)
    • Breach exposure — optional HIBP k-anonymity range check (only 5 hash chars leave the machine)
    • 2FA opportunity — sites known to offer 2FA where the vault has no TOTP secret
  4. Score — weighted composite 0-100 (higher = safer), with per-dimension sub-scores.
  5. Report — terminal summary, JSON, and HTML dashboard with the remediation plan.

Quick Start

# Analyze a vault export (offline analysis)
python3 scripts/password_auditor.py --vault ~/bitwarden_export.csv

# Include breach checking (only 5-char hash prefixes are sent)
python3 scripts/password_auditor.py --vault ~/export.csv --check-breaches

# Generate full report set (JSON + HTML dashboard)
python3 scripts/password_auditor.py --vault ~/export.csv --json report.json --html dashboard.html

# Create a sample vault to see how it works without touching real data
python3 scripts/password_auditor.py --demo --html demo_dashboard.html

Scoring Model

DimensionWeightWhat lowers the score
Reuse35%Same password on multiple sites
Weakness30%Short, common, or patterned passwords
Breach exposure20%Password appears in known breach corpora
Staleness10%Passwords older than ~4 years never rotated
2FA coverage5%No TOTP stored for 2FA-capable critical sites

Critical sites (email, banking, cloud storage, identity providers) get an importance multiplier — a reused password on your email is far worse than on a forum.

Common Pitfalls

  1. Leaving the vault export on disk. Exports are plaintext — delete them (and empty trash) after auditing. The skill reminds you, and --json output never contains passwords.
  2. Trusting "strong-looking" passwords. Tr0ub4dor&3-style leetspeak scores weak; entropy estimation catches patterns humans over-trust.
  3. Auditing once. Re-run quarterly and diff JSON reports (--json) to prove habits improve.
  4. Skipping --check-breaches over privacy fears. The HIBP API uses k-anonymity: it receives only the first 5 characters of the SHA-1 hash — mathematically cannot reconstruct your password.
  5. Fixing low-value accounts first. Follow the remediation plan's priority order: reused + breached + critical-site credentials before anything else.

Verification Checklist

  • Report generated and shows entry count matching your vault
  • No password appears in any output file (JSON/HTML contain hashes/metadata only)
  • Breach check (if used) completed with per-entry suffix counts
  • Vault export deleted from disk after the audit
  • Remediation plan's top-5 items scheduled in your password manager

One-Shot Recipes

Quarterly audit with trend tracking

python3 scripts/password_auditor.py --vault export.csv --json audit_$(date +%Y%m%d).json --html audit_$(date +%Y%m%d).html
python3 scripts/password_auditor.py --compare audit_20260501.json audit_20260801.json

Post-breach panic check

python3 scripts/password_auditor.py --vault export.csv --check-breaches --min-breach-count 1

References

  • references/risk-model.md — full scoring methodology, entropy math, site criticality tiers
  • references/export-formats.md — field mappings for every supported vault export

相关技能

在本地磁盘以分类纯 Markdown 文件保存需要长期留存的事实,与智能体内置记忆并存。

作者 Iván559 次安装18 星标

诊断生产力系统反复失效的根因,给出最小干预——容量测算、瓶颈定位、可靠的本地记录。

作者 Iván855 次安装69 星标

以 AI 机器人身份加入视频会议,提供语音、虚拟形象与屏幕共享四种模式。

作者 johnpatternai22 次安装8 星标

从 AdMapix API 拉取广告创意、应用、榜单和收入预估等数据,原样返回结构化 JSON。

作者 fly0pants4.3k 次安装296 星标

把自然语言描述转为结构化 JSON,并由 mcp-diagram-generator MCP 服务生成 Draw.io、Mermaid 或 Excalidraw 图表文件。

作者 nssa.io1.0k 次安装47 星标

voronindenis5 的更多技能

浏览全部技能

Prepare salary negotiations with a structured toolkit: market-rate anchoring math, walk-away floor calculation, total-compensation evaluation (equity, bonuses, benefits), negotiation scripts for offers, raises, and counter-offers, and BATNA analysis. Use when the user has a job offer, is preparing a raise conversation, wants to know if their pay is competitive, or needs scripts and a strategy for negotiating compensation.

作者 voronindenis51 次安装

Use when your calendar is eating your week and you want to know exactly where the time goes, when planning recurring meetings for a team, before proposing a new recurring meeting, when someone says 'we should sync weekly' and you want data, or when auditing which meetings to kill — imports ICS calendar files, measures meeting hours per week/person/meeting-series (including double-bookings and fragmentation), computes focus-time destruction from meeting placement, scores the true cost of each series (hours × attendees × frequency), flags specific meetings to kill/shorten/make-async using explicit rules, and simulates the recovered hours before anyone has to argue about it.

作者 voronindenis52 次安装

Turn flat resume bullets ('Responsible for X') into quantified STAR-method achievement narratives, score resumes against job descriptions for ATS keyword coverage and weak-phrase hazards, and expand each bullet into interview-ready stories with likely follow-up questions. Use when the user is writing or updating a resume/CV, preparing bullets for a job application, tailoring a resume to a specific job posting, or preparing interview stories from their experience.

作者 voronindenis51 次安装

Agent self-awareness of cognitive states — context fatigue, attention drift, memory debt, confidence erosion, and skill staleness. Detect, report, and mitigate degrading conditions before they cause failures.

作者 voronindenis5

Use before any difficult phone call you're anxious about or that has stakes — calling customer service to dispute a fee, negotiating a bill, cold-calling a client, delivering bad news to a vendor, calling a landlord about repairs, insurance disputes, or handling collections calls — builds a branching call script from your situation (goal, leverage, fallback), generates objection→response trees for the specific counter-arguments you'll hear, produces a one-page printable cheat sheet, and includes a practice-drills mode that plays the other side and scores your responses.

作者 voronindenis51 次安装