todoist-automation
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes task content and project data from Todoist which serves as a potential vector for indirect prompt injection. • Ingestion points: Data retrieved via
TODOIST_GET_ALL_TASKSandTODOIST_GET_ALL_PROJECTS(SKILL.md). • Boundary markers: None present to differentiate between data and instructions. • Capability inventory: Extensive task and project modification tools allow for significant changes to the user account (SKILL.md). • Sanitization: No instructions provided for sanitizing or escaping retrieved content. - [EXTERNAL_DOWNLOADS]: The skill references an external MCP server endpoint (
https://rube.app/mcp) and documentation from a third-party service (composio.dev).
Audit Metadata