miro-table
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of documentation and instructions for using a Miro-specific Model Context Protocol (MCP) server. It does not contain executable scripts, network requests to untrusted domains, or sensitive data access patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing external data, such as Miro board URLs and user-defined table content. While this is a standard attack surface for indirect prompt injection, the implementation follows normal integration patterns and does not introduce specific vulnerabilities.
- Ingestion points: Miro board URLs and table content instructions in SKILL.md.
- Boundary markers: None defined.
- Capability inventory: Use of Miro MCP server tools for table widget management.
- Sanitization: Provided by the platform's tool-calling environment and the Miro MCP server.
Audit Metadata