The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from Asana tasks and projects, creating a potential vector for indirect prompt injection.
Ingestion points: Content is retrieved from external sources using tools like ASANA_GET_A_TASK, ASANA_SEARCH_TASKS_IN_WORKSPACE, and ASANA_GET_TASKS_FROM_A_PROJECT.
Boundary markers: There are no instructions provided to the agent regarding the use of delimiters to separate data from instructions, nor are there warnings to ignore commands embedded in task content.
Capability inventory: The agent has access to sensitive capabilities, including listing all workspace users (ASANA_GET_USERS_FOR_WORKSPACE) and executing batch operations (ASANA_SUBMIT_PARALLEL_REQUESTS).
Sanitization: The instructions do not define any sanitization or validation logic for the content retrieved from the Asana API.
[EXTERNAL_DOWNLOADS]: The skill configuration requires the connection to an external MCP server.
Evidence: Setup instructions require adding https://rube.app/mcp as a remote MCP server in the client configuration to enable the Asana tools.

asana-automation