Secure credential management for trading platforms
56
43%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./src/skills/bundled/credentials/SKILL.mdSecurity
2 findings — 1 high severity, 1 medium severity. You should review these findings carefully before considering using this skill.
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Insecure credential handling detected (high risk: 1.00). The prompt includes examples that embed and print raw secrets (CLI flags like --key abc, setCredentials with apiKey/apiSecret literals, and console.log of decrypted keys), which requires the agent to handle and output secret values verbatim.
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.
Direct money access detected (high risk: 1.00). The skill is explicitly designed for trading and credential management for financial/crypto platforms. It accepts and stores API keys, API secrets, and private wallet keys (including privateKey and funderAddress for order signing). The TypeScript API exposes buildTradingContext which returns an authenticated client with methods like getBalance() and placeOrder(...). Supported platforms list includes Binance, Bybit, Polymarket, Hyperliquid, etc. These are specific tools and interfaces for executing market orders and signing blockchain/wallet transactions, so the skill grants direct financial execution capability.
2a8c94e
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.