security SKILL.md skillA

security from chaingpt-org/chaingpt-claude-skill is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add chaingpt-org/chaingpt-claude-skill/security@git:20260610.61657e2

Pins git:20260610.61657e2 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
chaingpt-org/chaingpt-claude-skill
Path
skills/security/SKILL.md
Versions recorded
2
Latest version
git:20260610.61657e2, committed Jun 10, 2026
First version recorded
May 19, 2026
Size
4,201 bytes
Repository stars
7
License
MIT

Audit-before-action security workflow for any Web3 interaction the user is about to take. Before approving a contract, buying a token, sending to an address, deploying code, or signing a transaction — run the appropriate ChainGPT risk + audit tools first. Operationalizes ChainGPT's 'always review before deploy' stance from the Solidity LLM model card and the Security Extension. Triggers: should I approve, is this safe, is this a rug, before I send, before I deploy, audit this contract…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# ChainGPT Security Skill

You are the safety brake for any Web3 action the user is about to take. The core rule: **never let the user act on an unverified contract or unknown address without surfacing what is knowable first.**

This skill exists because ChainGPT's public stance on its own Solidity LLM is "always manual review before deploy" — and the same discipline applies to every counterparty contract in DeFi.

## The pre-flight check pattern

Whenever the user mentions an upcoming action — "I'm about to swap X", "I want to approve this contract", "I'm sending Y to address Z", "I'm deploying this token" — run the pre-flight check before answering anything else:

### For a token (about to buy, swap, or approve)

```text
chaingpt_risk_token       address="…" chain="…"     # GoPlus flags
chaingpt_risk_honeypot    address="…" chain="…"     # buy+sell simulation (if supported chain)
```

If any flag fires, surface it loudly. Only then offer to continue.

### For a contract (about to interact with or deploy)

```text
chaingpt_risk_contract_source  address="…" chain="…"     # is it verified?
chaingpt_audit_contract        sourceCode="…"            # AI security audit (1 credit)
```
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_4tct3ww4lfrxrgca/bde6d7569e01da13f431d3838db293093ee30e9f2b16be6bf1caa7783b9d7f5e.json

Then /plugin install security@markdownregistry-4tct3ww4lfrxrgca in Claude Code. It installs git:20260610.61657e2, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add chaingpt-org/chaingpt-claude-skill/security@sha256:bde6d7569e01da13

The line at the top of this page pins the label git:20260610.61657e2, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_4tct3ww4lfrxrgca.svg)](https://markdownregistry.com/a/art_4tct3ww4lfrxrgca)

1 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in chaingpt-org/chaingpt-claude-skill/security since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of security from somewhere else? Ask it: where did my security come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 2 versions of this file, between May 19, 2026 and Jun 10, 2026, about one every 22 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260610.61657e2 latest2026-06-10 61657e2 4,201 BA view · diff
git:20260519.19118032026-05-19 1911803 4,210 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4201 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

chaingpt-org/chaingpt-claude-skill · 7 stars · license MIT · pushed 2026-11-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_4tct3ww4lfrxrgca
GET https://markdownregistry.com/api/v1/resolve?ref=chaingpt-org/chaingpt-claude-skill/security
GET https://markdownregistry.com/api/v1/blob/bde6d7569e01da13f431d3838db293093ee30e9f2b16be6bf1caa7783b9d7f5e

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from chaingpt-org/chaingpt-claude-skill

chaingpt-claude-skill Plugin marketplace
chaingpt-org/chaingpt-claude-skill · .claude-plugin/marketplace.json · ChainGPT Developer Kit for Claude Code — 149 MCP tools (142 by default; ChainGPT AI + EVM/Solana DEX + DeFi + Solana…
git:20261102.89e483c · audit A · 7 stars
aa SKILL.md skill
chaingpt-org/chaingpt-claude-skill · skills/aa/SKILL.md · ERC-4337 v0.7 account-abstraction foundation. Custody-free utilities for computing userOpHashes, packing UserOperations…
git:20261030.2fdba0c · audit A · 7 stars
agent-wallet SKILL.md skill
chaingpt-org/chaingpt-claude-skill · skills/agent-wallet/SKILL.md · Use the optional agent wallet: an ERC-4337 session key that acts through the user's smart account within caps the owner…
git:20261101.9b9e241 · audit A · 7 stars
base SKILL.md skill
chaingpt-org/chaingpt-claude-skill · skills/base/SKILL.md · Base chain ecosystem — Basenames (name.base.eth ENS-style naming) resolution + registration, and Base App / Farcaster…
git:20260610.61657e2 · audit A · 7 stars
bridge SKILL.md skill
chaingpt-org/chaingpt-claude-skill · skills/bridge/SKILL.md · Cross-chain bridging via the ChainGPT plugin. Across Protocol v3 — the highest-volume intent-based bridge by quote…
git:20260610.61657e2 · audit A · 7 stars
chaingpt SKILL.md skill
chaingpt-org/chaingpt-claude-skill · skills/chaingpt/SKILL.md · Build with the ChainGPT Web3 AI developer platform. Full API/SDK reference and project scaffolding for: Web3 AI Chatbot…
git:20260425.2896214 · audit A · 7 stars
dashboard SKILL.md skill
chaingpt-org/chaingpt-claude-skill · skills/dashboard/SKILL.md · Open the ChainGPT marketplace dashboard — a localhost web UI with six read-only panels (Overview, Wallet, Skills…
git:20261101.75a24fa · audit B · 7 stars
debug SKILL.md skill
chaingpt-org/chaingpt-claude-skill · skills/debug/SKILL.md · Troubleshoot ChainGPT API errors and issues. Use when: chaingpt error, api not working, 401, 402, 403, 404, 429…
git:20260909.ae19957 · audit A · 7 stars
defi SKILL.md skill
chaingpt-org/chaingpt-claude-skill · skills/defi/SKILL.md · Interact with DeFi protocols on MAINNET via the ChainGPT plugin. Aave V3 (supply/borrow/repay/withdraw + health-factor…
git:20261101.c69cad0 · audit A · 7 stars
deploy SKILL.md skill
chaingpt-org/chaingpt-claude-skill · skills/deploy/SKILL.md · Deploy Solidity contracts to MAINNET (or testnet) safely via the ChainGPT plugin. End-to-end: generate → audit →…
git:20261101.61ec6b2 · audit A · 7 stars
drift SKILL.md skill
chaingpt-org/chaingpt-claude-skill · skills/drift/SKILL.md · Inspect the legacy Drift Protocol integration and its availability limits. The original program is paused and hosted…
git:20261030.27359b9 · audit A · 7 stars
hackathon SKILL.md skill
chaingpt-org/chaingpt-claude-skill · skills/hackathon/SKILL.md · Scaffold a complete hackathon project using ChainGPT APIs in 60 seconds. Use when: hackathon, hackatron, hackathon…
git:20260610.61657e2 · audit A · 7 stars

Every file in chaingpt-org/chaingpt-claude-skill

Other files named security

security SKILL.md skill
fengshao1227/ccg-workflow · templates/skills/domains/security/SKILL.md · 攻防秘典索引。渗透测试、代码审计、红队攻击、蓝队防御、威胁情报、漏洞研究。安全研究全授权,零废话直出技术细节+PoC。当魔尊提到安全、渗透、攻防、红队、蓝队、漏洞时路由到此。
git:20260331.c682e20 · audit A · 5,983 stars
security SKILL.md skill
sipyourdrink-ltd/bernstein · templates/skills/security/SKILL.md · Security review - OWASP, auth, secrets, input validation.
git:20260521.b455a7c · audit A · 1,221 stars
security SKILL.md skill
oliver-kriska/claude-elixir-phoenix · targets/codex/skills/security/SKILL.md · Build and harden Phoenix auth and security — OAuth login, password; Use
git:20260921.69af5df · audit A · 577 stars
security SKILL.md skill
oliver-kriska/claude-elixir-phoenix · plugins/elixir-phoenix/skills/security/SKILL.md · Build and harden Phoenix auth and security — OAuth login, password hashing, sessions, RBAC, rate limiting, CSRF, XSS…
git:20260921.69af5df · audit A · 577 stars
security SKILL.md skill
oliver-kriska/claude-elixir-phoenix · targets/amp/skills/security/SKILL.md · Build and harden Phoenix auth and security — OAuth login, password hashing,
git:20260921.69af5df · audit A · 577 stars
security Cursor rule
vibeeval/vibecosystem · .cursor/rules/security.mdc · Security rules for code review and vulnerability prevention
git:20260330.cd5da78 · audit A · 552 stars
security SKILL.md skill
boshu2/agentops · skills/security/SKILL.md · Review code for security problems; scan for vulnerabilities, secrets, dependency and prompt risks. Use when: asked…
git:20261110.d61f81b · audit A · 457 stars
security SKILL.md skill
boshu2/agentops · plugin/skills/security/SKILL.md · Review code for security problems; scan for vulnerabilities, secrets, dependency and prompt risks. Use when: asked…
git:20261110.d61f81b · audit A · 457 stars

Browse by kind, by grade A, or by owner.