The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes content from ClickUp (such as task descriptions, comments, and document pages) which is external untrusted data.
Ingestion points: clickup_search, clickup_get_task, clickup_get_task_comments, and clickup_get_document_pages in app.py.
Boundary markers: Not explicitly defined in the skill instructions.
Capability inventory: The skill provides extensive capabilities to write to ClickUp (creating tasks, sending messages, attaching files) and interacts with the mcp-skill library.
Sanitization: No specific sanitization of the retrieved content is performed by the skill itself; it relies on the underlying agent's handling of tool outputs.

clickup