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

NoteDiscovery: why it is not safe to use

We found risky default auth, destructive note actions without documented confirmation, and first-run runtime downloads in local source setups.

What we found

Our review did not find hidden prompt instructions, undisclosed data exfiltration, obfuscated code, or access to unrelated local credentials. The main concerns were operational security defaults and action safety.

The reviewed materials show that NoteDiscovery can be configured with authentication disabled by default, along with placeholder or sample auth values such as the password `admin` and a non-random example secret key. We did not find real credentials in the repo, but these defaults would need to be changed before any network exposure.

We also found documented capabilities for deleting, moving, renaming, and publicly sharing notes, media, and folders, including deleting folders and their contents. In the reviewed docs, we did not see a required confirmation step for these potentially irreversible actions.

For local source runs, `run.py` is documented to auto-install missing Python requirements and trigger a vendor asset download script on first start. These remote fetches are disclosed, but they still add runtime network activity.

What to do instead

Use this skill only after enabling authentication, replacing all sample secrets and default passwords, and keeping the instance off the network until that is done. Prefer deployments with pinned, preinstalled dependencies and reviewed frontend assets rather than first-run downloads. Limit use to trusted note stores, and require human review before delete, move, rename, or public-sharing operations.

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

Source: https://github.com/gamosoft/NoteDiscovery

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.