Agent skill

Wallet Security News

by walletbeat in walletbeat/walletbeat

A skill your agent uses when a contributor wants to add a Wallet Security News entry to the walletbeat site.

MITAuto-check passed

Install Wallet Security News

skills CLI
$ npx skills add walletbeat/walletbeat --skill wallet-security-news -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install walletbeat/walletbeat wallet-security-news --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/walletbeat/walletbeat.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/wallet-security-news .claude/skills/wallet-security-news && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
wallet-security-news
GitHub stars
119
Token cost
~2.1k tokens
SKILL.md length
1,038 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when a contributor wants to add a Wallet Security News entry to the walletbeat site.

  • Works in 3 steps: Create the news file → Register it in the index → Add spelling exceptions (only if needed)
  • A contributor wants to add a Wallet Security News entry to the walletbeat site
  • SKILL.md covers Your first actions, What data to look for, References and File structure, plus 2 more sections
  • Calls pnpm; reaches trezor.io and x.com

What it does

Wallet Security News is an agent skill from walletbeat/walletbeat. Use when a contributor wants to add a Wallet Security News entry to the walletbeat site. Guides through reading the incident source, extracting the required data, classifying the incident (type, severity, impact, status), structuring the news file, registering it in the index, and verifying with the project checks. Works for hacks, data breaches, vulnerabilities, and general incidents, whether they affect a tracked wallet or not.

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: An open repository of EVM-compatible wallets 🌸. The licence is MIT.

When your agent uses it

  • A contributor wants to add a Wallet Security News entry to the walletbeat site

Example prompts

  • “/wallet-security-news”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Create the news file
  2. Register it in the index
  3. Add spelling exceptions (only if needed)

What it can do on your machine

Read from SKILL.md and the folder at commit c6104c7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pnpm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • trezor.io
    • x.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Wallet Security News loads about 2.1k tokens when it runs. Until then it costs about 114 tokens; SKILL.md has 1,038 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~114
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from walletbeat/walletbeat at commit c6104c7, republished under its MIT licence (© walletbeat). 1,038 words, ~2,138 tokens.

Download SKILL.mdSave it as .claude/skills/wallet-security-news/SKILL.md (or your agent's skills folder).
name
wallet-security-news
description
Use when a contributor wants to add a Wallet Security News entry to the walletbeat site. Guides through reading the incident source, extracting the required data, classifying the incident (type, severity, impact, status), structuring the news file, registering it in the index, and verifying with the project checks. Works for hacks, data breaches, vulnerabilities, and general incidents, whether they affect a tracked wallet or not.
argument-hint
[incident-url-or-description]

You are helping a contributor add a Wallet Security News entry to the Walletbeat project. The incident they want to record is: $ARGUMENTS (if blank, ask them for the incident URL or a description of the incident before proceeding).

You have explicit permission to create and edit files inside data/news/ and to edit data/news/index.ts and .cspell.json.

Your first actions

  1. If $ARGUMENTS is blank, ask: "Which incident would you like to add a security news entry for? Please share the announcement URL or a description."
  2. Read the source material. If a URL was provided, fetch the page (use the browser or curl). Extract the facts below from the article itself — do not guess.
  3. Read the schema and an example file so your entry matches the project conventions:
    • src/types/content/news.ts — the WalletSecurityNews type and all enums
    • data/news/index.ts — how entries are registered and sorted
    • One or two existing entries in data/news/ as style references (e.g. data/news/2026-01-06-global-e-breach.ts for a service-provider data breach, or data/news/2026-07-17-consensys-metamask-north-korean-hacker.ts for a wallet-company incident)

After reading these, summarize the facts you extracted and confirm the classification with the contributor before creating the file.


What data to look for

From the source, extract as many of these as the article supports:

  • Date of the incident / disclosure → publishedAt
  • Date of the last update (e.g. the publication date of the incident report, or today) → updatedAt
  • Affected wallet(s) → wallets. Map to the exact wallet ID (the filename of the wallet in data/software-wallets/, data/hardware-wallets/, or data/embedded-wallets/, e.g. metamask, ledger).
    • If the wallet is not tracked in the project (no wallet file exists), use wallets: [] — the entry is then a general incident. Do not invent an ID.
  • What happened → summary (2–3 sentences, objective, and factual)
  • A short headline → title
Classifying the incident

Use the enums in src/types/content/news.ts. When unsure, pick the most conservative matching value and confirm with the contributor.

  • type (NewsType) — how the event is categorized:
    • HACK — exploit/attack that stole crypto or wallet funds
    • DATA_BREACH — unauthorized exposure of personal information (not funds)
    • VULNERABILITY — discovered flaw, exploited or not
    • INCIDENT — general security event not covered above
  • severity (Severity) — CRITICAL / HIGH / MEDIUM / LOW, based on impact (funds at risk is high; a non-fund privacy exposure of emails is typically MEDIUM).
  • impact.category (ImpactCategory) — what kind of damage:
    • SEED_PHRASE_LEAK, PRIVATE_KEY_LEAK, SIGNING_BUG, SUPPLY_CHAIN, PRIVACY_LEAK, PHISHING_RELATED, HARDWARE_VULNERABILITY, VENDOR_INFILTRATION, OTHER
  • impact.fundsImpacted — true if user funds were affected or at risk, else false.
  • status (IncidentStatus) — RESOLVED / MITIGATED / ONGOING / DISPUTED. Use the value matching how much the article indicates the incident is addressed.

References

Every entry needs a ref (WithRef<WalletSecurityNews>) pointing at the primary source(s):

  • Prefer the official announcement / incident report from the wallet developer or the affected party (e.g. a blog post, a security advisory).

  • The ref.label should be a human-readable description of the link (e.g. the article's title), and ref.url the direct URL.

  • Add secondary refs (news coverage, affected-company advisories) only if they add meaningful detail.

  • To cite more than one source, make ref an array of labeled ref objects (each with label + url). E.g. a blog post plus the vendor's announcement on X:

    ts
    ref: [
      { label: 'Trezor blog: Recent customer data exposed in shipping provider incident', url: 'https://trezor.io/blog/news/...' },
      { label: 'Trezor on X: Customer data exposure incident', url: 'https://x.com/Trezor/status/...' },
    ],
  • refTodo / refNotNecessary are not appropriate here — the news entry should always cite the incident source.


File structure

1. Create the news file

Create a single file in data/news/:

data/news/YYYY-MM-DD-<slug>.ts
  • YYYY-MM-DD = the incident's publishedAt (when the incident occurred or was first disclosed).
  • <slug> = a short, kebab-case slug of the incident, matching the entry's slug field.

Example: data/news/2026-08-06-privy-metabase-security-incident.ts

The file exports a single default object as const satisfies WalletSecurityNews. Match the exact structure of existing entries — the object must include every WalletSecurityNews field (slug, type, ref, impact, publishedAt, severity, status, summary, title, updatedAt, wallets). Dates use YYYY-MM-DD strings.

Show full SKILL.md (439 more words)Show less
2. Register it in the index

In data/news/index.ts, add a dynamic import for the new file inside the allWalletSecurityNews array. Order in the array does not matter — the list is sorted by publishedAt at the end of the module.

3. Add spelling exceptions (only if needed)

If the source introduces proper nouns the project dictionary does not know (e.g. a vendor or tool name such as Metabase), add the word to the words array in .cspell.json, keeping it alphabetically sorted. Only add valid proper nouns — never add typos or arbitrary words.

Two gotchas when adding a word:

  • Add it in its canonical capitalization. Because cSpell matches words case-insensitively, one entry (ShipMonk) also covers the lowercased slug in the filename / index import (shipmonk) — don't add both spellings. Enter the word in its correct capitalization (the proper-noun form), not lowercase. Harper (the grammar linter, see tests/utils/grammar.ts) builds its vocabulary from the words list in .cspell.json. A capitalized entry is recognized as a proper noun, and Harper automatically adds its possessive 's form — so you don't need to add ShipMonk's. A lowercase entry would not be recognized as a proper noun.
    • Edge case: a brand spelled with a leading lowercase letter (e.g. imToken) trips Harper's Capitalization lint (it would force ImToken). Such words must also be added to PROPER_NOUNS_LOWERCASE_FIRST in tests/utils/grammar.ts — a code edit outside this skill's file permissions.
  • Exact sort order. The cSpell test sorts by toLowerCase() (tests/cspell.test.ts), so ordering can differ from a naive case-sensitive sort — e.g. ShipMonk (ship...) sorts after shefi and before sidepanel, not right after Shamir. If the order is wrong, pnpm check:vitest fails with a message naming the two words that are out of order; move it accordingly.

Testing and verification

Run the project checks after creating the entry:

bash
pnpm check:all

This must pass before the change is considered complete. Common failures specific to news entries:

  • Spelling — the check:spelling step flags unknown proper nouns. Fix by adding the term to .cspell.json.
  • Type errors — the default export must satisfy WalletSecurityNews. Missing fields, wrong enum values, or a slug mismatch between the filename and the slug field will fail to compile.

Key rules to remind the contributor throughout

  • Source the facts. The summary, dates, and classification must come from the article, not from assumptions.
  • wallets: [] is valid. An incident is still worth recording when it does not map to a tracked wallet — use an empty wallets array rather than an invented ID.
  • Dates are YYYY-MM-DD strings. publishedAt is the incident/disclosure date; updatedAt is the last-known-update date.
  • Always provide a ref. The news entry must cite the incident source — no refTodo.
  • Run pnpm check:all before opening a PR — it must pass.

© walletbeat, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/wallet-security-news of walletbeat/walletbeat.

Open the folder on GitHubat commit c6104c7

Compare with similar skills

Wallet Security News next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Wallet Security News compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Wallet Security News this skillwalletbeat/walletbeat119—~2.1kAutomated safety check: PassMIT
Competitor News MonitorNousResearch/hermes-agent252k—~1.2kAutomated safety check: PassMIT
Newsalsk1992/CloddsBot3k—~462Automated safety check: PassMIT
Changelog Entrysickn33/agentic-awesome-skills47k1 repos~1.1kAutomated safety check: PassMIT
Contributor Screendifferent-ai/openwork24k—~939Automated safety check: WarnCustom licence
Codewhale Contributor Onboardingcodewhale-hq/Codewhale41k—~1.3kAutomated safety check: PassMIT

Similar skills

  • Competitor News Monitor

    NousResearch/hermes-agent

    Watch named companies for material news; cited digests. An agent skill from NousResearch/hermes-agent.

    252k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • News

    alsk1992/CloddsBot

    Monitor news and correlate with prediction market movements. An agent skill from alsk1992/CloddsBot.

    3k GitHub stars~462 tokensUpdated 8 days ago
    Auto-check passed
  • Changelog Entry

    sickn33/agentic-awesome-skills

    Generate a properly formatted CHANGELOG.md entry in Keep a Changelog format from a commit range or PR.

    47k GitHub starsUsed in 1 repo~1.1k tokens
    DevelopmentAuto-check passed
  • Contributor Screen

    different-ai/openwork

    Screen a pull request from an outside contributor for hidden, obfuscated, or supply-chain-risky changes before any of its code runs.

    24k GitHub stars~939 tokensUpdated today
    DevelopmentAuto-check: warnings
  • Codewhale Contributor Onboarding

    codewhale-hq/Codewhale

    Reports whether a fresh Codewhale checkout is current, builds and passes its tests, and what changed since the contributor was last here, without touching the working tree.

    41k GitHub stars~1.3k tokensUpdated today
    DevelopmentAuto-check passed
  • Emblemai Crypto Wallet

    sickn33/agentic-awesome-skills

    Crypto wallet management across 7 blockchains via EmblemAI Agent Hustle API.

    47k GitHub starsUsed in 2 repos~669 tokens
    Business, Finance & HRAuto-check passed

More from walletbeat/walletbeat

  • Wallet Create

    walletbeat/walletbeat

    A skill your agent uses when a contributor wants to add a brand-new wallet to the walletbeat project.

    119 GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Wallet Update

    walletbeat/walletbeat

    A skill your agent uses when a contributor wants to populate or update feature data for a wallet that already exists in the Walletbeat project.

    119 GitHub stars~3.1k tokensUpdated today
    Auto-check passed
  • Wallet Data Collection

    walletbeat/walletbeat

    A skill your agent uses when asked to deal with a wallet's network traffic data, for automated analysis and classification.

    119 GitHub stars~568 tokensUpdated today
    Auto-check passed

Questions about Wallet Security News

What does Wallet Security News do?

A skill your agent uses when a contributor wants to add a Wallet Security News entry to the walletbeat site. Wallet Security News is an agent skill from walletbeat/walletbeat. Use when a contributor wants to add a Wallet Security News entry to the walletbeat site.

When should I use Wallet Security News?

Wallet Security News fits situations like: A contributor wants to add a Wallet Security News entry to the walletbeat site.

How do I install Wallet Security News in Claude Code?

Run `npx skills add walletbeat/walletbeat --skill wallet-security-news -a claude-code`. Or copy the skill folder (.agents/skills/wallet-security-news in walletbeat/walletbeat) into .claude/skills/wallet-security-news in your project. Claude Code loads it when a task matches its description.

How do I install Wallet Security News in Codex?

Run `npx skills add walletbeat/walletbeat --skill wallet-security-news -a codex`. Or copy the skill folder (.agents/skills/wallet-security-news in walletbeat/walletbeat) into .agents/skills/wallet-security-news in your project. Codex loads it when a task matches its description.

Can I use Wallet Security News in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add walletbeat/walletbeat --skill wallet-security-news -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wallet-security-news, .gemini/skills/wallet-security-news, .github/skills/wallet-security-news and .opencode/skills/wallet-security-news in your project.

What does Wallet Security News need to run?

Going by SKILL.md and its folder, Wallet Security News needs the command-line tools its instructions call (pnpm).

Does Wallet Security News access the network?

SKILL.md names 2 domains. In commands or code: trezor.io and x.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Wallet Security News safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Wallet Security News use?

Wallet Security News is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Wallet Security News use?

About 2.1k tokens (SKILL.md is roughly 8.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Wallet Security News?

Skills that share tags, products or a category with Wallet Security News: Competitor News Monitor (NousResearch/hermes-agent, 252k stars), News (alsk1992/CloddsBot, 3k stars), Changelog Entry (sickn33/agentic-awesome-skills, 47k stars) and Contributor Screen (different-ai/openwork, 24k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Wallet Security News?

walletbeat (a GitHub organization) maintains it in walletbeat/walletbeat, which has 119 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 10, 2026.

Source: walletbeat/walletbeat on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.