Todoist AI: why it is not safe to use
Todoist AI passed our review with disclosed network use, no hardcoded secrets, and no signs of hidden instructions or privilege abuse.
What we found
Our review of Todoist AI did not identify a security or privacy issue that would block use. The repository passed our checks for hidden instructions, hardcoded secrets, obfuscation, undisclosed remote code fetches, credential harvesting, and privilege escalation. Network destinations we observed were disclosed and matched the stated purpose: Todoist through the Todoist SDK and the named hosted MCP endpoint at `ai.todoist.net` for OAuth and MCP access.
The skill can create, modify, and delete Todoist data, which is expected for this category. In the reviewed code and documentation, we did not find evidence of covert data transfer outside Todoist. The README also advises users to verify which Todoist account is connected before write operations.
What to do instead
Use Todoist AI as a normal Todoist-connected skill, with the usual care for write access. Confirm the connected Todoist account before allowing changes or deletions, and provide only the Todoist token or OAuth access needed for this integration. If you need stricter controls, prefer read-only workflows or limit use to accounts and projects appropriate for automated task management.
Source: https://github.com/doist/todoist-ai
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.