todoist-automation

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface. It retrieves arbitrary text from a user's Todoist account (tasks, projects, sections) and uses it within the agent context. Malicious content in these fields could influence agent behavior.
  • Ingestion points: TODOIST_GET_ALL_TASKS, TODOIST_GET_ALL_PROJECTS, TODOIST_GET_ALL_SECTIONS (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: TODOIST_DELETE_TASK, TODOIST_DELETE_SECTION, TODOIST_UPDATE_TASK (SKILL.md).
  • Sanitization: Absent.
  • [EXTERNAL_DOWNLOADS]: The skill requires connecting to an external MCP server at https://rube.app/mcp. This server facilitates the connection between the agent and the Todoist API.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 12:44 AM