miro-automation

Warn

Audited by Snyk on Mar 5, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). SKILL.md explicitly requires calling MIRO_GET_BOARDS2 and MIRO_GET_BOARD_ITEMS (e.g., "find item by content" and resolve board names to IDs) which ingests user-generated Miro board/item content from third-party sources that could contain instructions influencing subsequent tool use.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). https://rube.app/mcp is explicitly required as the Rube MCP server and is queried at runtime (via RUBE_SEARCH_TOOLS) to fetch tool schemas that directly influence agent prompts and behavior, so it is a runtime external dependency that can control instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 07:55 AM