The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides tools to read and process data from Trello, which constitutes a potential surface for indirect prompt injection.
Ingestion points: Data retrieved from Trello card titles, descriptions, and comments through tools like TRELLO_GET_SEARCH and TRELLO_GET_BOARDS_CARDS_BY_ID_BOARD.
Boundary markers: The instructions do not include specific delimiters or prompts to ignore instructions that might be embedded within the Trello content.
Capability inventory: The skill includes tools for modifying Trello boards, such as TRELLO_ADD_CARDS and TRELLO_UPDATE_CARDS_BY_ID_CARD.
Sanitization: There are no explicit requirements for sanitizing the input from Trello before the agent uses it to perform actions.
[SAFE]: The skill configuration points to the Rube MCP server endpoint at https://rube.app/mcp and official documentation at composio.dev, which are consistent with its stated functionality and author context.

trello-automation