Spot vs Polymarket divergence trading on 15-minute crypto markets
74
63%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./src/skills/bundled/divergence/SKILL.mdSecurity
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
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.
Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests open third-party market data (Binance WebSocket via createCryptoFeed and Polymarket/Gamma markets via createMarketRotator and the ExecutionService) and uses those live prices to generate trading signals and execute orders, so untrusted public market content can materially influence agent actions.
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 a trading agent: it monitors Binance spot vs Polymarket, "Buys the lagging side and sells when it corrects," exposes commands to start/stop trading with a configurable trade size, shows positions/open trades, and has explicit risk-management actions (take-profit, stop-loss, trailing stop, time/force exits). It references market APIs (Polymarket/Gamma and Binance spot) and supports live execution (default dry-run but --dry-run optional), so its primary purpose is to place market orders and manage real trades. This constitutes 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.