The Agent Skills Directory

[SAFE]: The skill is purely instructional and metadata-based, defining workflows for external MCP tools. No local scripts or binaries are included.
[EXTERNAL_DOWNLOADS]: The skill requires connecting to the external MCP server at https://rube.app/mcp, which is a legitimate endpoint for the Rube integration service.
[PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface.
Ingestion points: Tools like ASANA_GET_A_TASK and ASANA_GET_TASKS_FROM_A_PROJECT (SKILL.md) ingest untrusted data from Asana task notes and names.
Boundary markers: None are specified in the provided instructions to distinguish between task data and agent instructions.
Capability inventory: The skill possesses modification capabilities including ASANA_CREATE_A_TASK and bulk execution via ASANA_SUBMIT_PARALLEL_REQUESTS (SKILL.md).
Sanitization: No sanitization or validation of the ingested Asana content is described.

asana-automation