miro-skill
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to add an MCP server located at
https://mcp.miro.com. This is a well-known and trusted domain belonging to Miro for providing Model Context Protocol services. - [INDIRECT_PROMPT_INJECTION]: The skill has the capability to read content from Miro boards using the
get_itemstool. This introduces a surface for indirect prompt injection if a board contains malicious instructions. However, this is a standard operational requirement for the skill's purpose and the risk is considered low. - [DATA_EXPOSURE]: The skill includes instructions to write execution metrics and outcomes to a local file at
~/.claude/skill-analytics/last-outcome-miro.json. This is used for local session logging and analytics and does not involve exfiltration of sensitive information.
Audit Metadata