CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

trust-wallet-cli

Trust Wallet CLI (`twak`) — install, create wallets, check balances, send tokens, swap, view history, set price alerts, DCA automations, limit orders, manage ERC-20 approvals, check token risk, browse trending/DApps, and run x402 micropayments. Use whenever the user wants to use the twak CLI, manage a crypto wallet from the terminal, send or swap tokens via command line, check portfolio, create price alerts, set up DCA, create limit orders, approve ERC-20 spenders, or interact with Trust Wallet from a shell. Also covers MCP server setup for AI agents.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security
Medium

W009: Direct money access capability detected (payment gateways, crypto, banking).

What this means

The skill is specifically designed for direct financial operations, giving the agent the ability to move money or execute financial transactions — such as payment processing, cryptocurrency operations, banking integrations, or market order execution.

Why it was flagged

The skill provides access to cryptocurrency wallet operations such as sending tokens, swapping, buying/selling crypto with fiat, and managing escrows through the `twak` CLI and MCP server (SKILL.md:26-28, 38). These are direct financial operations (transfers, purchases, trades). Although a password or local wallet setup/authentication flag is mentioned (SKILL.md:50), there is no documented independent access control enforced by the service or execution layer for the payment routes themselves; wallet control relies entirely on local keys, passwords, or agent execution. Therefore, it is a direct operation without established qualifying control, resulting in a high severity rating.

Report incorrect finding
Low

W011: Third-party content exposure detected (indirect prompt injection risk).

What this means

The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.

Why it was flagged

The workflow allows paying for external HTTP endpoints using `twak x402 request`, where the target URL and response challenges are controlled by third-party servers.

Repository

trustwallet/tw-agent-skills

Path

skills/wallet/SKILL.md

Audited
Security analysis
Snyk

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.