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

Kroger MCP: why it is not safe to use

Warned because it stores Kroger OAuth tokens and local shopping state in JSON files on the device, which may increase local privacy exposure.

What we found

Our review did not find hidden prompts, hardcoded secrets, dangerous system actions, remote code execution, or access to unrelated credential stores. Network activity appeared consistent with the skill's grocery-shopping purpose, limited to Kroger API calls and product images hosted by Kroger.

The main issue we found is local credential and state handling. The skill reads its Kroger API client ID and secret from environment variables or local config, then stores OAuth tokens and local shopping state in JSON files on the device. We did not see evidence that it accesses browser passwords, SSH keys, or other system credential stores. Even so, storing tokens and shopping state in local files can increase privacy exposure on shared, backed-up, or poorly secured machines.

What to do instead

Use this skill only in an environment you control, with file access limited to your user account. Prefer short-lived or easily revocable Kroger credentials, and rotate them if the device is shared or compromised. Review where the JSON files are stored, avoid syncing them to broad cloud backups if not needed, and delete local token and shopping-state files when you are done.

Want the same outcome, safely? Use our checked skill instead.

Source: https://github.com/CupOfOwls/kroger-mcp

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.