todoist
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
todoist-ts-clipackage from the npm registry, which is a standard and well-known service. - [COMMAND_EXECUTION]: The skill interacts with the user's task data by executing the
todoistbinary for various task-related operations. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its processing of external task data.
- Ingestion points: Task titles, project names, and comments are fetched from the Todoist API via commands like
todoist tasksandtodoist comments. - Boundary markers: No boundary markers or 'ignore' instructions are used when displaying task content to the agent.
- Capability inventory: The skill can perform network operations via the
todoistCLI to modify user data. - Sanitization: Content from the Todoist API is processed as-is without sanitization.
Audit Metadata