miro-format
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a workflow for ingesting user-provided content to seed new Miro documents, tables, or diagrams, which creates a potential surface for indirect prompt injection.
- Ingestion points: User input defining the content to seed into Miro items in the
Workflowsection ofSKILL.md. - Boundary markers: The instructions lack explicit delimiters or specific guardrails to isolate user-supplied data from the agent's instructions.
- Capability inventory: The skill utilizes Miro MCP tools to perform write operations (creation and seeding) on Miro items.
- Sanitization: There are no instructions for validating or sanitizing the content before it is processed by the Miro tools.
Audit Metadata