The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process content from Monday.com boards, items, and updates. Since this data is often provided by multiple users in a collaborative environment, it serves as a vector for indirect prompt injection attacks where malicious instructions hidden in board items could hijack the agent's logic.
Ingestion points: Data enters the agent's context through tools such as MONDAY_LIST_BOARD_ITEMS, MONDAY_ITEMS_PAGE, MONDAY_LIST_SUBITEMS_BY_PARENT, and MONDAY_BOARDS (metadata), all of which reside in the SKILL.md workflows.
Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or ignore instructions that might be embedded within the retrieved Monday.com data.
Capability inventory: The skill has broad capabilities including creating and modifying items, boards, and groups across several scripts, and it provides a raw GraphQL interface via MONDAY_CREATE_OBJECT for complex operations.
Sanitization: There is no evidence of sanitization, escaping, or validation logic to filter out potentially malicious content from the external data before it is used to drive subsequent agent actions.

monday-automation