todoist
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses a CLI tool (@useclawlink/cli) and infrastructure (claw-link.dev) belonging to the vendor to manage Todoist data. The authentication process and local credential storage are standard for CLI-based service integrations.
- [COMMAND_EXECUTION]: The skill performs actions by executing the ClawLink CLI via shell commands for all task management functions.
- [EXTERNAL_DOWNLOADS]: The setup instructions use npx to fetch the @useclawlink/cli package from the NPM registry.
- [PROMPT_INJECTION]: The skill ingests untrusted data from Todoist tasks and comments in SKILL.md (ingestion points). No explicit boundary markers are defined in the CLI command templates. The skill provides capabilities to read and write to the Todoist API (capability inventory). Sanitization is expected to be performed by the agent context management.
Audit Metadata