security

security is a command for Claude Code from trustwallet/tw-agent-skills. It costs 66 tokens per session (551 once invoked), scanned A, original, MIT.

Commands for checking whether a cryptocurrency address or token shows signs of risk. The checks can identify flags such as scams, sanctions, honeypots, freeze controls, or missing security information.

In plain words
What is it for?
Use it to validate wallet and transaction addresses, inspect token risk, check whether a token can restrict selling or freeze funds, review audit and contract signals, and look for known malicious labels.
Why use it?
It provides security information before sending money to an unfamiliar address or trading an unfamiliar token.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/trustwallet/tw-agent-skills/security
Clone the repo
git clone --depth 1 https://github.com/trustwallet/tw-agent-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for security

README.md
[![agentmods](https://agentmods.dev/badge/commands/trustwallet/tw-agent-skills/security.svg)](https://agentmods.dev/commands/trustwallet/tw-agent-skills/security)
Your own site
<a href="https://agentmods.dev/commands/trustwallet/tw-agent-skills/security"><img src="https://agentmods.dev/badge/commands/trustwallet/tw-agent-skills/security.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 551 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00066 $0.00551
Opus 5 $0.00033 $0.00275
Sonnet 5 $0.00013 $0.00110
Haiku 4.5 $0.00007 $0.00055

Measured 5d ago against content hash 06a42b4fd7c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/security.md · 47 lines

What it actually says

Security

Validate addresses and analyze token risk before transacting. This is the safety net — use it proactively before swaps or transfers to unfamiliar addresses/tokens.

Base URL: https://tws.trustwallet.com Auth: HMAC-SHA256 (run /setup first if you haven't configured auth)

Validate Address — GET /v1/validate

Check if an address is safe, flagged, or sanctioned.

Param Required Description
address Yes Address to validate
asset_id No Asset ID for context (e.g., c60)
type No address or transaction

Example: GET /v1/validate?address=0xd8dA...&asset_id=c60&type=address

Result values: whitelist (known safe), neutral (no signals), blacklist (known malicious), unknown (insufficient data)

Also returns is_contract, is_sanctioned, risk_score, and labels.

Check Token Risk — GET /v2/coinstatus/{assetId}

Deep security analysis for a token — critical before interacting with any new or unverified token.

Param Required Description
version No Use 2
include_security_info No Include EVM security data (default: true)
include_solana_security_info No Include Solana security data (default: true)

Example: GET /v2/coinstatus/c60_t0xdAC17F958D2ee523a2206206994597C13D831ec7?version=2&include_security_info=true

Risk levels: low, medium, high, critical, unknown

EVM security signals: isHoneypot, hasAudit, auditProvider, hasMintFunction, canTakeBackOwnership, isTradingCooldown, warnings

Solana security signals: hasFreezeAuthority, hasMintAuthority, isInitialized, warnings

For full response schemas, read skills/api/references/security.md.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 47 lines · 66 tokens per session scan A 06a42b4fd7c7

Subscribe to this mod's changes

security is a command published in the GitHub repository trustwallet/tw-agent-skills (96 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 551 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.