The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources, which could potentially contain malicious instructions intended to influence the agent's behavior.
Ingestion points: In SKILL.md, the skill uses miro_list_board_items to read the content of external Miro boards to understand the current modeling state. It also performs web searches using Perplexity or WebSearch tools to gather domain context.
Boundary markers: The instructions do not specify the use of delimiters (such as XML tags or triple quotes) or explicit "ignore embedded instructions" warnings when processing the data retrieved from Miro or the web.
Capability inventory: The skill possesses network capabilities through its integration with the Miro MCP server and search tools (WebSearch, WebFetch, Perplexity). It also has the ability to generate documents using the document-skills plugin (e.g., pptx, docx, pdf).
Sanitization: There is no evidence of input validation, escaping, or filtering of the external content before it is interpolated into the agent's reasoning process for recommending workshop steps.

event-storming