asana-automation
Pass
Audited by Gen Agent Trust Hub on Apr 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs users to configure an external MCP server endpoint. This endpoint (https://rube.app/mcp) provides the tool definitions and connection management for Asana automation.
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external data from Asana.
- Ingestion points: Tools such as ASANA_GET_A_TASK and ASANA_SEARCH_TASKS_IN_WORKSPACE read user-controllable data (task names, notes) from Asana.
- Boundary markers: Absent. No explicit delimiters or instructions are used to separate untrusted data from agent instructions.
- Capability inventory: The skill utilizes tools to create, modify, and manage tasks, projects, and sections within the user's Asana workspace.
- Sanitization: Absent. No input validation or sanitization of the retrieved data is specified in the workflows.
Audit Metadata