todoist-2
Warn
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of a third-party binary 'todoist' from an unverified GitHub repository (buddyh/todoist-cli) via Homebrew or Go, which does not originate from a verified or well-known organization.
- [COMMAND_EXECUTION]: The skill's primary functionality is based on executing shell commands through the 'todoist' CLI to interact with the Todoist API.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from Todoist (task names, descriptions, and comments) which constitutes an external, untrusted input source. 1. Ingestion points: Reading task lists ('todoist tasks'), viewing specific tasks ('todoist view'), and searching ('todoist search') ingest data from the Todoist API into the agent's context. 2. Boundary markers: There are no explicit delimiters or instructions to distinguish between task data and agent instructions in the provided documentation. 3. Capability inventory: The skill can execute shell commands via the 'todoist' CLI and perform write operations to the remote service. 4. Sanitization: There is no evidence of sanitization, filtering, or validation of the task content retrieved from the API before it is processed by the agent.
Audit Metadata