AgentPod is building a private, secure device for your AI agent.The AgentPod device is coming.Coming soonBe first
We checked this and rejected itprivacy

Viral finance-related skill trend: Freqtrade trading-bot skill is showing up on OpenAgentSkill: why it is not safe to use

A crypto trading bot skill called Freqtrade is trending on OpenAgentSkill, raising routine privacy and financial safety questions for users.

What happened

OpenAgentSkill’s live trending page currently lists Freqtrade as a trending AI agent skill. The page describes it as a “Free, open source crypto trading bot,” shows 4 events over 2 days, labels it a production candidate, and includes an install command that would pull the skill from its upstream repository.

That does not by itself mean the skill is unsafe. But it does mean people may see it, install it quickly, and consider connecting it to exchange accounts.

What it means for you

If you use an AI agent like Claude Cowork, Claude Code, or Codex, this is the kind of skill that deserves extra caution before use. A trading skill can be money-moving or money-adjacent automation, meaning it may influence trades or handle account access tied to real funds.

In practice, that can expose sensitive data such as API keys, account balances, strategy files, and transaction history. API keys are secret codes that let software access your account. If a skill gets broad permissions, mistakes or misuse could affect both privacy and finances.

What to do instead

Pause before connecting any exchange account or sharing keys. Check what permissions are required, and avoid giving withdrawal access if it is not necessary. Use a separate test account or read-only access where possible. Keep strategy files and account history private unless you fully understand why they are needed.

If you want lower-risk options, AgentPod lists only reviewed, tested skills. That is not a promise of zero risk, but it gives normal users a calmer starting point than installing a fast-rising skill straight from a trending page.

Sources:

  • https://www.openagentskill.com/trending?lang=zh

Source: https://www.openagentskill.com/trending?lang=zh

We report what our security review found at the time we checked, with the goal of keeping people safe. Projects change; if a maintainer has since fixed this, we are glad to recheck it. Email hello@agentpod.com.

Copied to clipboard. Paste it into your AI (ChatGPT, Claude, or your agent) to add the skill.